Undergraduate Project (UG)

Permanent URI for this communityhttps://dspace.summituniversity.edu.ng/handle/123456789/8

Browse

Now showing 1 - 20 of 113

A COMPARATIVE STUDY OF LOGISTIC REGRESSION AND XGBOOST FO A COMPARATIVE STUDY OF LOGISTIC REGRESSION AND XGBOOST FOR CREDIT CARD FRAUD DETECTION R CREDIT CARD FRAUD DETECTION
(2024) KESHINRO OLUSHOLA SAMUEL
Since the dawn of recorded human history, fraud has entailed a variety of dishonest behaviors that vary greatly in their forms and tactics. Almost every purchase made today is done so online. Online transactions are completed using an easy-to-use, multi-party, straightforward approach that does not require the usage of cash. The annual loss resulting from fraudulent credit card transactions is in the billions. According to the 10th annual study on online fraud, between 2006 and 2008, 1.4% of online payments resulted in lost money; nevertheless, the real percentage of lost revenue increased as online sales increased. The annual loss resulting from fraudulent credit card transactions is in the billions. The 10th annual study on online fraud states that while 1.4% of online payments resulted in lost money between 2006 and 2008, the real percentage of lost revenue increased as online sales increased. The present dataset for this study was collected in September 2013 through credit card transactions made through Kaggle by cardholders throughout Europe. In this study, a model built with Logistic Regression techniques was compared to the XGBoost model that was based on standard evaluation criteria.
A FACE DETECTION AND RECOGNITION-BASED ONLINE ATTENDANCE SYSTEM USING COMPUTER VISION
(2023) NAFISAH, ADEDAYO SULAIMAN.
Face recognition has drawn a lot of attention recently and is a crucial issue in many applications, including access control, security systems, and credit card verification and identification of criminals. This study suggests three primary subsystems, including autonomous door access control, face detection, and face recognition. By adapting the principal component analysis (PCA) approach to the fast based principal component analysis (FBPCA) approach, the face identification and detection process is achieved. The captured image is recognized using a web camera and compared with the image in the database. To achieve the goal of identification, image processing and recognition are applied to the actual image modification and transformation. This project focuses on the design and of a facial recognition attendance system using computer vision technique. The system aims to automate the process of identifying and verifying individuals in an organization based on their facial features. By leveraging advanced algorithms, image processing techniques, and deep learning models, the system achieves accurate and real time facial recognition. The project involves data collection, pre-processing, feature extraction, and system integration to develop a comprehensive facial recognition solution
A HYBRID LINEAR PROGRAMMING MODEL AND GENETIC ALGORITHM APPROACH FOR RESOURCES ALLOCATION IN DISASTER RESPONSE
(2023) SHOBAYO, SULAIMON
Efficient allocation of resources such as emergency personnel and equipment plays a major role in disaster scenarios by minimizing the response time. Limited resources concerns using resources as productively as possible. This research focuses on novel development of a hybrid linear programming model and genetic algorithm approach for resource allocation in accident disaster response. The objective is to optimize the total response-time for allocation of resources to affected areas and populations and enhance the efficiency and effectiveness of disaster response operations. This model combines the strengths of integer linear programming, which provides a systematic framework for the minimization of the total response time, and the Genetic Algorithms, which handle the case of complex and dynamic problem spaces. The GA leverages on the model formulated in the ILP trade-off to handle the complex based spaces which are utilized to search for near-optimal solutions within the problem space. The model considers various factors such as distance between resources and number of affected areas, capacity of affected area, and resource capacities. The objective function minimizes the response time by optimizing the distance between the resources and number of affected areas, while the constraints are, resources allocation, and capacity area. The result shows an improved and efficient outcome to response operations in minimizing response time to reaching affected area and maximizing coverage area with available resources. The outcomes enables decision-makers to make informed and optimized choices during critical situations by improving overall response outcome.
ADOPTING ARTIFICIAL INTELLIGENCE TO SOLVE ELECTORAL CHALLENGES IN NIGERIA
(2023) OWOLABI HABEEB BABAJIDE
The study examined the deployment of artificial intelligence (AI) to solve electoral challenges in Nigeria. AI can assist in data management and result collation, enabling faster and more efficient processing, reducing human errors, and enhancing transparency. The adoption of artificial intelligence in Nigeria electoral systems is a growing global trend which has been of use among most developed countries for a free, fair and credible elections The objectives of the study were to address electoral irregularities, find out voters perceptions and acceptance towards the deployment of artificial intelligence and investigate the citizens on how artificial intelligence can curb electoral challenges. This study made use of quantitative method and a survey method was used to analyze the data derived from respondents through administered of questionnaires online. A total number of 385 eligible voters were administered questionnaires online, subjecting the population to the krejcie and Morgan table. The study found out that there is positive responses and acceptance from the respondents towards the deployment of artificial intelligence to curb electoral irregularities in Nigeria. Also, there’s a positive outlook among respondents that adopting artificial intelligence can bring about transparent, free, and fair elections to Nigeria. The study therefore recommends that there should be effective rules and regulations guiding the use of AI in the electoral process and employ well trained personnel in the system for transparency and accountability, there should be no network glitch while transmitting the results online, there should be enough security so there won’t be any form of hacking, there’s still need for more voter education towards the use of these mechanisms in a violent free society, the governing body of the electoral process should be totally independent, and the leaders should not be appointed by the government of the day.
ADOPTION AND USAGE OF ARTIFCIAL INTELLIGENCE FOR JOURNALISTIC PRATICES AMONG JOURNALISTS IN KWARA STATE.
(2024) ADELODUN, Aminat Ayinke
The study examined the perceived effect of artificial intelligence on ethical journalism among journalists in Kwara State. The objectives of the study were to (i) determine the level of awareness of artificial intelligence for journalistic practice among journalists in Kwara State. (ii) examine the artificial intelligence tools for journalistic practice among journalists in Kwara State. (iii) determine the usage of artificial intelligence tools for the journalistic practice among journalists in Kwara State (iv) determine the effect of artificial intelligence on journalistic practice on journalists in Kwara State. This study made use of Cross-sectional research design and survey research was adopted as the research method. Two hundred and five available journalists constituted the population of the study. A total of one hundred and thirty-four served as the sample size which was drawn from the total population of Journalists in Kwara State by subjecting the population to the Krejcie and Morgan table. Questionnaires were used to collect data which was analyzed with statistical methods indicating frequency, percentages, mean, and standard deviation. The study found that there is a positive perception and a notable level of awareness, among journalists in Kwara State regarding artificial intelligence tools for journalistic practice. Also, there is a positive outlook among journalists in Kwara State towards various artificial intelligence tools used for journalistic practice. Moreso, journalists in Kwara State have a high level of usage of artificial intelligence, as they actively incorporate AI tools into their daily work routines, lastly, artificial intelligence tools have significantly enhanced the speed and efficiency of news gathering and production, leading to improved accuracy and fact-checking in journalism practices in Kwara State. The study, therefore, recommends that; media organizations should foster more public awareness about AI's role in journalism to foster trust and understanding among audiences. Communicate how AI tools enhance accuracy, storytelling, and data analysis in news reporting, and invest in training programs to upskill journalists on how to effectively use artificial intelligence tools for their reporting, as this will empower journalists to make the most out of AI technologies and leverage them to enhance the quality of their stories.
AMELIORATION OF ISOPROTENOL-INDUCED CARDIAC INJURY ON FEMALE WISTAR RATS BY AQUEOUS ETHANOLIC EXTRACT OF CARICA PAPAYA LEAVES.
(2024) IBRAHIM, MUSLIMAH GBEMISOLA.
: Conventional methods of nanoparticle synthesis often rely on the use of toxic chemicals, raising environmental concerns. This study shows the green synthesis of cobalt oxide nanoparticles (CoONPs) using extracts from Khaya Senegalensis (African mahogany) and Psidium guajava (guava) leaves. This plant extracts act as reducing and capping agents, removing the need for toxic chemicals. The research further investigates the possible application of these bio-synthesized CoONPs in soil bioremediation. The advantages of this method shows eco- friendly synthesis of nanoparticles, using plant extracts makes the process less toxic. The study would likely detail the characterization of the synthesized CoONPs using techniques such as UV-Visible spectroscopy, Fourier Transform Infrared Spectroscopy (FTIR), X-ray Diffraction (XRD), and Scanning Electron Microscopy (SEM) with Energy Dispersive X-ray spectroscopy (EDX) to determine their size, morphology, and other properties. The bioremediation approach using cobalt oxide nanoparticles helps in degrading the pollutants present in the soil.
AN IMPROVED ARTIFICIAL INTELLIGENCE MODEL FOR CYBER SECURITY INCIDENT RESPONSE AND RECOVERY SYSTEM
(2024) ASIMI OLALEKAN IDRIS
Cyber security incident response and recovery systems are currently facing a number of challenges that are different from the fast growth of advanced cyber threats to the complexity faced in coordinating an effective response across the various technological environments. Several techniques have been developed, but there are problems in the detection and mitigation of emerging threats in real-time, thus, organizations are at risk of data breaches, financial losses, and reputational damage. This study presents an improved Artificial Intelligence model that assists in effective incidence response and recovery from previously known and unknown threats. The bagging ensemble approach is adopted using Naïve Bayes, Decision Tree, Support Vector Machine and Neural Network as base classifiers to form the model. In the experiment, the dataset used has a total of 22544 instances and 42 attributes. The result gives 98.69% accuracy with ROC and PRC Area both 0.999. The Recall and F-Measure are both 0.987.
ANALYZING CUSTOMER SUPPORT LOGS FOR ANOMALY DETECTION USING DEEP LEARNING
(2024) ISSA, SHAMSUDEEN ENIOLA
This project investigates the application of deep learning techniques for anomaly detection in customer support logs, a critical resource for insurance companies. The increasing volume of customer interactions generates vast amounts of data, making it challenging to manually identify irregularities that may indicate fraud or data entry errors. By leveraging advanced data-driven methods, we developed a robust deep learning model capable of analysing historical support logs to detect anomalies with high accuracy. The study employs various neural network architectures, including convolutional and recurrent networks, to capture complex patterns within the data. We also explore feature engineering techniques to enhance model performance and ensure the reliability of the detection process. The results demonstrate significant improvements in identifying anomalies compared to traditional methods, underscoring the potential of deep learning in automating and streamlining customer support operations. Furthermore, the project emphasizes the importance of enhancing data quality, implementing real-time detection systems, and automating alerts to improve overall customer support efficiency. By addressing these challenges, our findings contribute to the development of more effective strategies for managing customer interactions and safeguarding against potential fraud, ultimately leading to better service delivery and customer satisfaction.
ANALYZING THE CAPITAL STRUCTURE EFFECT IN FINANCIAL STABILITY OF FIRMS IN COSUMER GOODS SECTORS USING ARTIFICIAL INTELLIGENCE
(2023) AJADI MARYAM OMOLOLA
Artificial intelligence (AI) is the capacity of a machine to display traits similar to those possessed by humans. This study has examined the capital structure effect on the financial stability of firms classified under consumer goods of the Nigerian exchange group. Secondary data based on extracts from annual report and accounts of selected consumer goods firms listed on the Nigeria exchange group market have been used in this study. Multiple regression method will be employed to analyse the relationships between the dependent and independent variables. The model will be estimated using E-view packages (version 7.0). (i) to figure out how debt-to-equity ratio and return on assets for consumer goods companies relate to one another, and (ii) to figure out how interest coverage affects return on assets for consumer goods companies (iii) the debt-to-equity ratio and the return on assets of companies that produce consumer items do not significantly correlate and (iv) In Nigeria, interest coverage has no appreciable impact on how well businesses function in the consumer products market. Additionally, in agreement with numerous empirical research on capital. This analysis supports the a priori association between leverage and company performance in a sample of Nigerian companies. Leverage is said to have a favourable effect on a company's performance, but the degree to which it does so depends on the return on assets (ROA) and liquidity of the companies. Findings from the analysis will reveal if capital structure has significant impact on financial performance of consumer goods firms in Nigeria. This study will also give recommendations for both government and firms in order to increase firm's performance level.
ANTIBIOGRAM OF ISOLATED BACTERIA FROM SELECTED SACHET WATER IN OFFA, KWARA STATE AND DATASET COLLECTION FOR PREDICTIVE MODEL
(2023) LAWAL, AISHAT BOLANLE
In Nigeria, sachet water is the only reliable source of drinking water. Aiming to evaluate the prevalence and antibiogram of bacteria isolated from specific brands of sachet water in Offa, Kwara State, this study attempts to evaluate the health concerns posed by diseases contracted from eating contaminated water internationally. Ten different brands of sachet water available in Offa, Kwara state, were examined using established techniques to ascertain the pH and bacteriological purity. Two bacterial isolates were characterized by sequencing the 16S rDNA using the universal primers 27F and 1492R to amplify the 16S target region. All the samples were clear and odourless with the exception of Sc4. Antibiotic susceptibility testing was performed using the disc diffusion method. Some bacterial isolates cannot be taxonomically identified from phenotypic characteristics. The water samples' pH values ranged from 1.7 to 7.0. Out of the ten water samples, bacterial growths were found in every single one. The range of the total heterotrophic count in cfu/ml was 2.0 to 5.8. Most of the water samples contained coliforms, with a value ranging from 1.1 to 7.0x103 cfu/ml. Staphylococcus aureus, Pseudomonas sp, Alcaligenes feacalis, Bacillus cereus, Proteus vulgaris, and Escherichia coli were among the isolates that were detected. Most isolates were shown to be extremely susceptible to ciprofloxacin, ofloxacin, and gentamycin while being resistant to ceftriazone sulbactam, cefotaxime, and amoxicillin clavulanate. Except for Escherichia coli, the majority of the isolates were susceptible to Gentamycin (GN), and all but one of them were resistant to Ceftriaxone sulbactam. Since none of the sachet water samples examined in this study met WHO standards for drinking water, routine monitoring of sachet water makers ought to be mandated.
ANTIBIOTICS PROFILING OF BACTERIA ISOLATED FROM CATFISH HARVESTED FROM AFELELE RIVER
(2022) ADERINKOLA, Adenike Tayibat
Fishes are cheap sources of protein and are commonly reared in aquaculture systems such as rivers in Nigeria. Bacterial infested fishes have been a serious public health concern. This study was aimed at isolating and identifying bacteria associated with the internal organs (gills, intestine, guts) of Clarias gariepinus (African Catfish) in Afelele river in Offa, kwara state, Nigeria. In addition, the bacterial load of the organs and antibiotic susceptibility profile of the isolates to conventional antibiotics were determined. An African catfish was sampled from the river. Bacteria isolated on Mac-Conkey agar and Nutrient agar plates were identified based on morphological and biochemical characteristics. Susceptibility of the isolates to antibiotics was carried out using the Kirby-Bauer disc diffusion method. Isolates from the fish organs include species of Vibrio, Aeromonas, Pseudomonas, Klebsiella, Staphylococcus, Serratia, Proteus, Bacillus, Streptococcus and Micrococcus. Results also revealed that there was significant difference in the bacterial load recovered from the fish organs (gut, gill and intestine). Serratia sp. was the most abundant gram positive bacterium in the organs of the fish sample, while Pseudomonas sp., a gram negative organism, appeared in the intestine and gut. Percentage susceptibility of the bacteria to antibiotics was highest with Ciprofloxacin and Gentamycin (85%) and least with Ampicillin and Vancomycin (75.0%). The most susceptible isolates were species of Bacillus and Klebsiella while Staphylococcus specie was the most resistant bacterium. This study has shown that high bacteria load are found in the internal organs of the fish and a good number of the bacteria are resistant to some of the antibiotics tested. Therefore, there is a need for adherence to proper sanitary measures to avoid bacterial contamination of fish.
ANTIMALARIAL ACTIVITY AND ITS EFFECT IN LIVER FUNCTION INDICES OF SAPONIN-RICH EXTRACT OF Euphorbia heterophylla LEAF IN Plasmodium berghei-INFECTED MICE
(2021) ADEJUMOBI, HASSAN ADEBISI
Malaria still continues to be a menace globally despite several efforts in curtailing it. The antimalarial activity and effect in liver function indices of Saponin-rich extract of Euphorbia heterophylla leaf in plasmodium berghei- infected mice was evaluated. Thirty mice were divided into six groups. The mice in group I (control) were uninfected, while those of groups II–VI were infected intraperitoneally with standard (2 ×10^7) inoculums of chloroquine sensitive Plasmodium berghei (NK65) parasite. Mice in groups I (control) and II (P. berghei-infected) received 0.2 ml of distilled water orally, while those of groups III–VI were treated orally with 20mg/kg body weight (b.w.) chloroquine and 2.5, 5 and 10 mg/kg b.w of saponin-rich extract of Euphorbia heterophylla leaf respectively for six days following the establishment of parasitaemia. The extract at all doses significantly (p < 0.05) decreased the percentage parasitaemia, and as well suppressed parasite growth and multiplication particularly at 10mg/kg. There was a significant decrease (p < 0.05) in the concentration of protein, globulin while there is significant increase (p < 0.05) in the concentration of serum and liver of aspartate aminotransferase, alanine aminotransferase and alkaline phosphatase activities when compared with the distilled water administered mice. FT-IR analysis of the saponin revealed the existence of aromatic compounds, alcohols, phenols alkyl groups, alkanes, primary amines, alphatic amine and alkyl halide groups which maybe adduced to the effect demonstrated by the extract.
ANTIMICROBIAL EFFECTS OF SOME SELECTED ESSENTIAL OILS AGAINST SKIN PATHOGENS WITH THE COLLATION OF DATASET AND PREDICTIVE MODELS
(2023) ADEKUNLE, HALIMA ITUNU
Essential Oils (EOs) are concentrated natural extracts derived from plants, which were proved to be good source of antimicrobial properties. The study followed the effect of some commonly used essential oils against some of the most common pathogenic bacteria. The various oils used were Castor oil. Almond oil, Olive oil and Carrot oil against selected skin pathogens namely; Staphylococcus aureus, Corynebacterium diphtheria, Bacillus subtilis, Aeromonas and Pseudomonas aeruginosa. The collected isolates were confirmed using biochemical and microbiological tests. Carrot oil had the highest inhibiting activity against Bacilli and Corynebacterium with the value of 20mm while Almond oil and olive oil had no inhibition zone (NZ) against Corynebacterium and Pseudomonas. Ciprofloxacin was the control used and it showed significant inhibition against the clinical isolates. Olive oil had the lowest inhibition ranging from 5mm to 10mm. Combinatorial effect of the essential oils showed no antimicrobial activity against the isolates depicting antagonistic effects of the essential oils. In conclusion, carrot oil and castor oil had higher activity while almond oil and olive oil had the lowest activity against the selected clinical isolates.
ANTIOXIDANT ACTIVITIES, PHYTOCHEMICAL COMPOSITION, GCMS AND FTIR ANALYSES OF AQUEOUS LEAF EXTRACT OF Euphorbia heterophylla
(2024) ALAWODE, TITILAYO LATIFAT
This study investigated the antioxidant potential and phytochemical composition of aqueous leaf extract from Euphorbia heterophylla. In vitro Antioxidant activity was evaluated using standard methods. Gas Chromatography-Mass Spectrometry (GC-MS) analysis was employed to identify the bioactive compounds present in the extract. The FTIR spectrum confirmed the presence of alcohols, phenols, alkanes, aliphatic amines, alkyl groups and aromatic compounds in extract. The results of the GC/MS analysis of the aqueous leaf extract provided different peaks determining the presence of 39 bioactive compounds. The results revealed significant antioxidant properties of the extract, which can be attributed to the presence of various compounds identified through GC-MS and FTIR analysis. These findings suggest that Euphorbia heterophyllapossesses promising antioxidant activity and could be a potential source of natural antioxidants.
ANTIOXIDANT AND ANTIDYSLIPIDEMIC EFFECT OF ETHANOLIC EXTRACT OF Monodora myristiica SEED IN TYPE 2 DIABETIC WISTAR RATS
(2023) OSENI, BARAKAT
Diabetes mellitus is a type of metabolic condition of elevated blood glucose with increase in prevalence and death rates in all geographical areas. This project examined the antioxidant and antidyslipidemic effects of oral administration of ethanolic extract of Monodora myristica seed intype 2 diabetic (T2DM) rats. Induction of T2DM was done by feeding the rats with high fat diet followed by intraperitonial administration of 30 mg streptozotocin in citrate buffer solution. Forty male wistar rats were randomized into eight groups of five rats. The first group was non-diabetic rats and received 0.5 mL distilled water, the second was diabetic and received 0.5 mL of distilled water, the third-eighth groups were diabetic rats treated with metformin, 25, 50, 100 mg/kg body weight of the extract and 10 and 20 mg of selenium nanoparticles respectively for fourteen days. Findings from the result showed increased levels of serum total cholesterol, triacylglycerides, low density lipoprotein and malondialdehyde. Administration of the extract and selenium nanoparticles brought about a decrease in these levels. The antioxidant status of the diabetic rats were reduced, however there were not significant (P>0.05) differences in the reduced glutathione (except the 10 mg selenium nanoparticles), glutathione S-transferase and peroxidase activities but a significant (P<0.05) decrease in superoxide dismutase and catalase activities when compared to the diabetic untreated rats. Conclusively, this study further corroborates the potentials of the seed in mitigating lipid-associated diabetic disorders and suggestive of its advantage as food supplement in the management of diabetes complications.
APPLICATION OF ANIMATION TO TEACHING (A CASE STUDY OF SUMMIT UNIVERSITY, OFFA, KWARA STATE)
(2022) RAJI MUBARAK AKINOLA
Computer-mediated teaching & learning in higher institutions classroom is much relevant in recent times. Effective, efficient and knowledge-driven classroom teaching should not be limited to mere chalk, board and teacher relationship. Animation made Teaching and learning innovative, enjoyable, impacting and understandable. Whiteboard animation is a kind of animation that enable teaching with broad explanation, making it suitable for the creation of the videos in this project. Whiteboard animated videos were designed and created for selected course in the department of computer science. The videos were uploaded on a Youtube channel to aid easy access. The video’s texts were implemented using Adobe After Effect and the voiceover were recorded with Adobe Audition. Animated videos will enhance teaching in a wide range if it is adopted in every educational level.
ARTIFICIAL INTELLIGENCE AND CHALLENGES OF INSECURITY IN NORTH-EASTERN NIGERIA
(2023) ABDULHAMEED OLANREWAJU OLAITAN
Insecurity in Nigeria has resulted to the nasty destruction of life and property due to lack of proactive measures. This study examines how artificial intelligence can be effectively utilized to address security concerns, identifies challenges, limitations, and evaluates the effectiveness of AI-based approaches in mitigating insecurity in the North-Eastern Nigeria. The region has been facing significant security challenges, including boko insurgency, kidnapping and herdsmen and farmers crisis, which have resulted in loss of lives, displacement of peoples, and food insecurity. The research draws from secondary sources, including academic papers, official reports, personal observation and relevant government documents. The findings of this study contribute to the understanding of AI's role in conflict resolution and security enhancement in the North-Eastern Nigeria context. The objectives of the study were to: (i) examine the origin of Boko Haram Insurgency in North-Eastern Nigeria; (ii) identify various factors that triggered Boko Haram Insurgency in North-Eastern Nigeria;(iii) critically analyze how does Artificial Intelligence serves as an alternative approach in solving problem of insecurity in Nigerian; (iv) examine the strategies and efforts of stakeholders in restoring security and well-being among affected states. Based on the study's findings, the government should consider investing and providing each Divisional Security Headquarters with AI based technologies for monitoring their respective areas of command. Addressing ethnic and religious tensions in North-Eastern Nigeria is crucial for promoting security and social cohesion in the region. In addition to traditional approaches, leveraging artificial intelligence (AI) can play a significant role in tackling these issues. AI technologies can assist in fostering inclusivity, promoting interfaith dialogue, protecting minority rights, and enhancing community development.
ARTIFICIAL INTELLIGENCE AS A TOOL FOR NEWS GATHERING AMONG JOURNALISTS IN OSUN STATE
(2023) AKOLADE Barakat Olamide
This research work was designed to examine artificial intelligence as a tool for news gathering among journalists in Osun State. The study selected Osun State with sole focus on Osogbo where most of the journalists are practicing. In realizing this, three key research objectives were formulated which are; to identify an AI-driven driven tool that journalists in Osun State can use to gather news stories, to create an AI tool that can facilitate the gathering of news from multiple sources efficiently and to assess the level of effectiveness of an AI driven tool in gathering news. These objectives were reconstructed as the research questions for the study. The concepts of artificial intelligence and journalism practice, news gathering, the role of artificial intelligence in news gathering, awareness of artificial intelligence for news gathering and gatekeeping theory was adopted as appropriate theory for the work. Survey research method was used with the aid of questionnaires to gathered relevant information from the respondents in Osogbo. The study concluded that, artificial intelligence is an effective tool that has aided the journalists in Osun State in the areas of news gathering and presentations to the general public in the state. Part of it recommendation was, the Nigerian Union of Journalists to adopts artificial intelligence for news gathering and dissemination in the state and ensure that they recommended for their colleagues as a means of gathering information for effective journalism
ARTIFICIAL INTELLIGENCE BASED IRIS SEGMENTATION
(2023) SAHEED GANIYAT YAHAYA
The iris, a colored component of the eye surrounding the pupil, possesses a unique and distinctive pattern for each individual. Iris segmentation plays a pivotal role in the field of biometric. It serves as a critical stage in iris recognition systems, separating the iris area from other parts of the eye image, thereby enhancing the effectiveness of subsequent stages. In this paper, we propose a fusion-based iris segmentation technique that combines Thresholding and Limbic Pupil Boundary (LPB) methods. We evaluate the robustness of our approach using the CASIA and Ayush datasets. Specifically, we perform a comparative analysis on the Ayush dataset, comprising 650 eye images. The results of the evaluation demonstrate that the proposed approach accurately segments the iris from the eye image, laying the foundation for a reliable recognition system
ARTIFICIAL INTELLIGENCE FOR POST-PANDEMIC ASSESSMENT OF COVID- 19 VACCINATION UPTAKES IN SELECTED UNIVERSITIES IN KWARA STATE
(2024) ABDULHAMID, Khadijah Aliyu
Vaccination is aimed at averting the spread of COVID-19, but complications like vaccine hesitancy and resistance continue to arise, particularly in low-middle-income countries (LMIC) like Nigeria. This study examines factors contributing to vaccine hesitancy and the effectiveness of various communication strategies intended to promote vaccination. Through questionnaires distributed across four institutions in Kwara state, 201 participants were recruited. Most of the responded were between age 26-40 years where 95% were students, thus emphasizing the focus of the study on the student population. A smaller proportion consists of lecturers (3%) and non-teaching staff (2%). Females accounted for 58.2% while males had 41.8% of the population, indicating a relatively balanced gender representation within the study. The survey showed that only 42.7% received the COVID-19 vaccine, of these vaccinated participants, 53.4% received up to the second dose. While only 10.5% of participants had been fully immunized (AstraZeneca, Moderna, Pfizer-BioNTech, Johnson and Johnson). The most recurrent factors affecting the uptake of the COVID-19 vaccine among vaccine recipients were Friends and families (58.1%), Social media (5.1%), Personal decision (34.9%), Work (5.8%), The study found that the p-value, for significance regarding the factors influencing vaccination uptake is below 0.05. This suggests that the connections between the variables examined (like awareness, perception, and readiness to get the COVID-19 vaccine) and vaccination uptake are statistically significant, at a 5% level of significance. In addition, a predictive model was created with the help of machine learning techniques to predict vaccination trends, with precision pinpointing specific areas that require focused interventions. The research highlights the importance of public education and the promising role that artificial intelligence can play in improving vaccination strategies and overall public health results.