Yazar "Ajibade, Samuel-Soma M." seçeneğine göre listele
Listeleniyor 1 - 20 / 23
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe An Analysis of Social Networking for E-learning in Institutions of Higher Learning using Perceived Ease of use and Perceived Usefulness(Phcog.Net, 2022) Ajibade, Samuel-Soma M.; Adhikari, Nirmal; Ngo-Hoang, Dai-LongHigher education students and faculty use Facebook and Twitter. Researchers have also looked at social networking platforms in higher education. Social media has facilitated student-professor communication, collaboration, and engagement. To embrace students and teachers who utilize technology to learn and teach, it must be determined what influences their readiness to do so. This report tests the adoption of social networking media for e-learning in Nigerian utilizing the Technology Acceptance Model (TAM), which emphasizes perceived ease of use, perceived usefulness, and behavioural intention to utilize new technologies. Surveys were utilized for quantitative research. This study polled teachers and students from 4 Nigerian schools. Structural Equation Modeling was used to anticipate the model’s recommended factors (SEM). The study indicated that students’ and teachers’ behavioral intentions to use social media for e-learning in Nigerian universities are influenced by perceived ease of use and perceived usefulness.Öğe An analysis of the impact of social media addiction on academic engagement of students(ResearchTrentz Academy Publishing Education Services, 2022) Ajibade, Samuel-Soma M.; Mejarito, Cresencio; Egere, Odafe Martin; Adediran, Anthonia Oluwatosin; Gido, Nathaniel G.; Bassey, Mbiatke AnthonyThe study's goal is to comprehend how internet addiction affects students' academic performance. However, very few research has been able to explain how excessive internet use causes students to lose interest in their academic work. Many studies have examined the detrimental association between addictions and academic performance. This research consists of two factors: internet addiction (emotional and cognitive preoccupation with internet and loss of control and interference with daily life) and academic engagement (enthusiasm and commitment). Through questionnaires, data was gathered from 186 students at a higher institution in Nigeria. Both correlation and regression were used to evaluate the data. The results of the investigation demonstrated that internet addiction significantly and unfavorably affects enthusiasm and commitment. It's interesting to note that internet obsession on an emotional or cognitive level was not shown to be a reliable indicator of internet addiction or loss of control.Öğe Analysis of ımproved evolutionary algorithms using students' datasets(IEEE, 2022) Ajibade, Samuel-Soma M.; Ayaz, Muhammad; Ngo-Hoang, Dai-Long; Tabuena, Almighty C.; Rabbi, Fazle; Tilaye, Getahun Fikadu; Bassey, Mbiatke AnthonyEvolutionary Algorithms (EAs) are powerful heuristic search approaches which relies on Darwinian evolution that capture global solutions to complex optimization problems which has powerful features of reliability and versatility. (EAs) such as Particle swarm optimization (PSO) is a global optimization method that is extremely effective. PSO's flaws include slow convergence, premature convergence, and getting stuck at local optima. In this paper, chaotic map and dynamic-weight Particle Swarm Optimization (CHDPSOA) are combined with PSO to enhance the search strategy through adjusting the inertia weight of PSO and changing the position update formula in the (CHDPSOA), resulting in efficient balancing for local and global PSO feature selection processes. The performance of CHDPSOA was compared to that of three metaheuristic techniques: Differential Evolution (DE) and the original PSO, using eight numerical functions. The validation of this technique is carried out on four different datasets. The results show that the CHDPSOA is a good feature selection technique that balances the exploration and exploitation search processes to produce good results. The proposed CHDPSOA method performed well in correctly categorizing features using the KNN Classifier for all four datasets.Öğe Application of Machine Learning in Energy Storage: A Scientometric Research of a Decade(Springer Science and Business Media Deutschland GmbH, 2024) Ajibade, Samuel-Soma M.; Bashir, Faizah Mohammed; Dodo, Yakubu Aminu; Dayupay, Johnry P.; De La Calzada, Limic M.; Adediran, Anthonia OluwatosinThe publication trends and bibliometric analysis of the research landscape on the applications of machine/deep learning in energy storage (MES) research were examined in this study based on published documents in the Elsevier Scopus database between 2012 and 2022. The PRISMA technique employed to identify, screen, and filter related publications on MES research recovered 969 documents comprising articles, conference papers, and reviews published in English. The results showed that the publications count on the topic increased from 3 to 385 (or a 12,733.3% increase) along with citations between 2012 and 2022. The high publications and citations rate was ascribed to the MDLES research impact, co-authorships/collaborations, as well as the source title/journals’ reputation, multidisciplinary nature, and research funding. The top/most prolific researcher, institution, country, and funding body on MDLES research are; is Yan Xu, Tsinghua University, China, and the National Natural Science Foundation of China, respectively. Keywords occurrence analysis revealed three clusters or hotspots based on machine learning, digital storage, and Energy Storage. Further analysis of the research landscape showed that MDLES research is currently and largely focused on the application of machine/deep learning for predicting, operating, and optimising energy storage as well as the design of energy storage materials for renewable energy technologies such as wind, and PV solar. However, future research will presumably include a focus on advanced energy materials development, operational systems monitoring and control as well as techno-economic analysis to address challenges associated with energy efficiency analysis, costing of renewable energy electricity pricing, trading, and revenue prediction.Öğe Application of Machine Learning in Renewable Energy: A Bibliometric Analysis of a Decade(Institute of Electrical and Electronics Engineers Inc., 2023) Ajibade, Samuel-Soma M.; Flores, Denis Dante Corilla; Ayaz, Muhammad; Dodo, Yakubu Aminu; Areche, Franklin Ore; Adediran, Anthonia Oluwatosin; Oyebode, Oluwadare Joshua; Dayupay, Johnry P.Machine learning studies in the field of renewable energy are analysed here (REML). So, from 2012 to 2021, we looked at the publication tendencies (PT) and bibliometric analysis (BA) of REML research that was indexed by Elsevier Scopus. Key insights into the research landscape, scientific discoveries, and technological advancement were revealed by BA, while PT highlighted REML's important players, top cited papers, and financing organisations. In total, the PT discovered 1,218 works, 397 of which were conference papers and 106 were reviews. Because it spans the disciplines of science, technology, engineering, and mathematics, REML research is exhaustive, varied, and consequential. The most productive researchers, countries, and sponsors include Ravinesh C. Deo, the United States' National Renewable Energy Laboratory, and China's National Natural Science Foundation. Journal prestige and open access are valued by contributors, as seen by the success of Applied Energy and Energies. Productivity among REML's key stakeholders is boosted by collaborations and research funding. Keyword co-occurrence analysis was used to categorise REML research into four broad topic areas: systems, technologies, tools/technologies, and socio-technical dynamics. According to the results, ML plays a crucial role in the prediction, operation, and optimisation of RET as well as the design and development of RE-related materials.Öğe Bibliometric survey on particle swarm optimization algorithms (2001-2021)(HINDAWI LTD, 2022) Ajibade, Samuel-Soma M.; Ojeniyi, AdegokeParticle swarm optimization algorithms (PSOA) is a metaheuristic algorithm used to optimize computational problems using candidate solutions or particles based on selected quality measures. Despite the extensive research published, studies that critically examine its recent scientific developments and research impact are lacking. Therefore, the publication trends and research landscape on PSOA research were examined. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and bibliometric analysis techniques were applied to identify and analyze the published documents indexed in Scopus from 2001 to 2021. The published documents on PSOA increased from 8 to 1,717 (21,362.50%) due to the growing applications of PSOA in solving computational problems. "Conference papers" is the most common document type, whereas the most prolific researcher on PSOA is Andries P. Engelbrecht (South Africa). The most active affiliation (Ministry of Education) and funding organization (National Natural Science Foundation) are based in China. The research landscape on PSOA revealed high levels of publications, citations, and collaborations among the top authors, institutions, and countries worldwide. Keywords co-occurrence analysis revealed that "particle swarm optimization (PSO)" occurred more frequently than others. The findings of the study could provide researchers and policymakers with insights into the prospects and challenges of PSOA research relative to similar algorithms in the literature.Öğe Boosting enabled efficient machine learning technique for accurate prediction of crop yield towards precision agriculture(Springer Nature, 2024) Nagesh, O. Sri; Budaraju, Raja Rao; Kulkarni, Shriram S.; Vinay M.; Ajibade, Samuel-Soma M.; Chopra, Meenu; Jawarneh, Malik; Kaliyaperumal, KarthikeyanDue to the limited availability of natural resources, it is essential that agricultural productivity keep pace with population growth. Despite unfavorable weather circumstances, this project's major objective is to boost production. As a consequence of technological advancements in agriculture, precision farming as a way for enhancing crop yields is gaining appeal and becoming more prevalent. When it comes to predicting future data, machine learning employs a number of methods, including the creation of models and the acquisition of prediction rules based on past data. In this manuscript, we examine various techniques to machine learning, as well as an automated agricultural yield projection model based on selecting the most relevant features. For the purpose of selecting features, the Grey Level Co-occurrence Matrix method is utilised. For classification, we make use of the AdaBoost Decision Tree, Artificial Neural Network (ANN), and K-Nearest Neighbour (KNN) algorithms. The data set that was used in this study is simply a compilation of information about a variety of topics, including yield, pesticide use, rainfall, and average temperature. This data collection consists of 33 characteristics or qualities in total. The crops soya beans, maze, potato, rice, paddy, wheat, and sorghum are included in this data collection. This data collection was made possible through the collaboration of the Food and Agriculture Organisation (FAO) and the World Data Bank, both of which make their data available to the public. The AdaBoost decision tree has achieved the highest level of accuracy possible when used to anticipate agricultural yield. Both the accuracy rate and the recall rate are quite high at 99 percent.Öğe Computational model of recommender system intervention(Hindawi Limited, 2022) Ojeniyi, Adegoke; Ajibade, Samuel-Soma M.; Obafunmiso, Christiana Kehinde; Adegbite-Badmus, TawakalitA recommender system is an information selection system that offers preferences to users and enhances their decision-making. This system is commonly implemented in human-computer-interaction (HCI) intervention because of its information filtering and personalization. However, its success rate in decision-making intervention is considered low and the rationale for this is associated with users' psychological reactance which is causing unsuccessful recommender system interventions. This paper employs a computational model to depict factors that lead to recommender system rejection by users and how these factors can be enhanced to achieve successful recommender system interventions. The study made use of design science research methodology by executing a computational analysis based on an agent-based simulation approach for the model development and implementation. A total of sixteen model concepts were identified and formalized which were implemented in a Matlab environment using three major case conditions as suggested in previous studies. The result of the study provides an explicit comprehension on interplaying of recommender system that generate psychological reactance which is of great importance to recommender system developers and designers to depict how successful recommender system interventions can be achieved without users experiencing reactance and rejection on the system.Öğe A computer-aided feature-based encryption model with concealed access structure for medical Internet of Things(Elsevier Inc., 2023) Vaidya, Sumit; Suri, Ashish; Batla, Vishnu; Keshta, Ismail; Ajibade, Samuel-Soma M.; Safarov, GiyosiddinOne of the Internet of Things (IoT) security issues is the secure sharing and granular management of data access. This study recommends a feature-based encryption scheme with a hidden access structure for medical IoT data security. While establishing fine-grained access control of ciphertext data, the system can guarantee clinical client data privacy. First, it is recommended to convert identity-based encryption (IBE) into a feature-based encryption model (FBEM) using a universal conversion technique that supports multi-valued attributes and gates. IBE characteristics could be inherited by the converted FBEM. The conversion method is then used to change the receiver anonymous IBE scheme into the FBEM scheme with concealed access structure. The FBEM model is then used to construct the IoT scenario for the smart medical application. Theoretical analysis and experimental findings reveal that the suggested system provides advantages over prominent systems regarding computing efficiency, storage load, and security when the access structure is disguised.Öğe Data classification technique for assessing drug use in adolescents in secondary education(ResearchTrentz Academy Publishing Education Services, 2022) Ajibade, Samuel-Soma M.; Oyebode, Oluwadare Joshua; Dayupay, Johnry P.; Gido, Nathaniel G.; Tabuena, Almighty C.; Kilag, Osias Kit T.The reasons why students abuse drugs are crucial information. Knowledge of the difficulties associated with drug use can be improved by employing data mining techniques, which have many advantages. The focus of this study is to examine the causes of drug abuse among Lagos's high school students usingdata mining methods. In February of 2021, a cross-sectional study was conducted. Four hundred teenagers and young adults were present. They were given a questionnaire to fill out about their drug use habits, the types of drugs they take, and why they takethem. We found that 59.1% of students drank alcohol, 23.6 % smoked cigarettes, 15.4 % used cannabis, and 3.1% used cocaine. In addition, the performance of 5 classifiers is compared in terms of correctly classified instances (CCI), with all of them performing better than the simplest classifier (more frequent category: used drug/never used drugs) in terms of the percentage of correctly classified instances. KNN yielded the highest CCI across the board when various drugs were compared (alcohol: 82.40 percent, tobacco: 66.22 percent, cannabis: 91.16 percent, and cocaine: 94.24). Use motives obtained a higher classifier performance when it came to alcohol and tobacco use, but the opposite was true for cannabis and cocaine. Peer pressure and the community in which a teen lives are two major factors that we found to have a significantimpact on that teen's drug use.Öğe Data mining analysis of online drug reviews(Institute of Electrical and Electronics Engineers Inc., 2022) Ajibade, Samuel-Soma M.; Zaidi, Abdelhamid; Tapales, Catherine P.; Ngo-Hoang, Dai-Long; Ayaz, Muhammad; Dayupay, Johnry P.; Aminu Dodo, Yakubu; Chaudhury, Sushovan; Adediran, Anthonia OluwatosinData mining methods like sentiment analysis provide useful information. This paper examines drug online user reviews. This research predicts user satisfaction with sentiments and applied drugs on effectiveness and side effects using sentiment analysis based on classification and analyzes model transfer across data sources like Emzor and May & Baker data. Online medication review data. Web crawlers was used to collect the ratings and comments of forum members. Emzor Pharmaceutical Company had 463 reviews and May & Baker Pharmaceutical Company had 421 reviews. Data was split 70% for training and 30% for testing. We used sentiment analysis to predict user ratings on overall satisfaction, side effects, and drug efficacy. Emzor data performs better 89.1% in-domain sentiment analysis, while May & Baker data accuracy is 86.90% overall. In cross-data sentiment analysis, the Emzor and May & Baker data performed well when the trained model was applied to side effects. This study acquired data by trawling an internet drug review forum. This study shows that transfer learning can leverage cross-domain similarities to analyze cross-domain sentiment.Öğe Feature Selection for Metaheuristics Optimization Technique with Chaos(Institute of Electrical and Electronics Engineers Inc., 2022) Chaudhury, Sushovan; Oyebode, Oluwadare Joshua; Ngo Hoang, Dai-Long; Rabbi, Fazle; Ajibade, Samuel-Soma M.Particle swarm optimization (PSO) is a global optimization method that is extremely effective. PSO's flaws include slow convergence, premature convergence, and getting stuck at local optima. In this paper, the chaos map and dynamic-weight Particle Swarm Optimization (CPSO) are combined with PSO to improve the search process by adjusting the inertia weight of PSO and changing the position update formula in the Chaos dynamic-weight Particle Swarm Optimization (CPSO), resulting in efficient balancing for local and global PSO feature selection processes. Using eight numerical functions, the performance of CPSO was compared to that of two metaheuristic techniques which are the original PSO and Differential Evolution (DE). The results reveal that the CPSO is an efficient feature selection technique that generates good results by balancing the exploration and exploitation search processes.Öğe Gaussian map to improve firefly algorithm performance(Institute of Electrical and Electronics Engineers Inc., 2022) Rabbi, Fazle; Ayaz, Muhammad; Dayupay, Johnry P.; Oyebode, Oluwadare Joshua; Gido, Nathaniel G.; Adhikari, Nirmal; Tabuena, Almighty C.; Ajibade, Samuel-Soma M.; Bassey, Mbiatke AnthonyFirefly Algorithm (FA) mimics firefly behavior by flashing and attracts them. Firefly's global search mobility is improved for dependable global optimization using chaotic maps in this work. Investigations of benchmark problems with chaotic maps are carried out in depth. The system uses eight separate chaotic maps to fine-tune the firefly's enticing movements. By using planned chaotic transmissions instead of fixed values, the new method beats classic firefly methods. According to statistical data and the success rates of FA, the new algorithms improve the solution's performance and the reliability of global optimality.Öğe Improvement of Population Diversity of Meta-heuristics Algorithm Using Chaotic Map(Springer Science and Business Media Deutschland GmbH, 2022) Ajibade, Samuel-Soma M.; Ogunbolu, Mary O.; Chweya, Ruth; Fadipe, SamuelParticle swarm optimization (PSO) is a global optimization and nature-inspired algorithm known for its good quality and easily applied in various real-world optimization challenges. Nevertheless, PSO has some weaknesses such as slow convergence, converging prematurely and simply gets stuck at local optima. This study aims to solve the problem of deprived population diversity in the search process of PSO which causes premature convergence. Therefore, in this research, a method is brought to PSO to keep away from early stagnation which explains premature convergence. The aim of this research is to propose a chaotic dynamic weight particle swarm optimization (CHPSO) wherein a chaotic logistic map is utilized to enhance the populace diversity within the search technique of PSO with the aid of editing the inertia weight of PSO in an effort to avoid premature convergence. This study additionally investigates the overall performance and feasibility of the proposed CHPSO as a function selection set of rules for fixing problems of optimization. 8 benchmark functions had been used to assess the overall performance and seek accuracy of the proposed (CHPSO) algorithms and as compared with a few other meta-heuristics optimization set of rules. The outcomes of the experiments show that the CHPSO achieves correct consequences in fixing an optimization and has established to be a dependable and green metaheuristics algorithm for selection of features.Öğe Machine Learning Applications in Renewable Energy (MLARE) Research: A Publication Trend and Bibliometric Analysis Study (2012–2021)(MDPI, 2023) Ajibade, Samuel-Soma M.; Bekun, Festus Victor; Adedoyin, Festus Fatai; Gyamfi, Bright Akwasi; Adediran, Anthonia OluwatosinThis study examines the research climate on machine learning applications in renewable energy (MLARE). Therefore, the publication trends (PT) and bibliometric analysis (BA) on MLARE re search published and indexed in the Elsevier Scopus database between 2012 and 2021 were examined. The PT was adopted to deduce the major stakeholders, top-cited publications, and funding organi zations on MLARE, whereas BA elucidated critical insights into the research landscape, scientific developments, and technological growth. The PT revealed 1218 published documents compris ing 46.9% articles, 39.7% conference papers, and 6.0% reviews on the topic. Subject area analysis revealed MLARE research spans the areas of science, technology, engineering, and mathematics among others, which indicates it is a broad, multidisciplinary, and impactful research topic. The most prolific researcher, affiliations, country, and funder are Ravinesh C. Deo, National Renewable Energy Laboratory, United States, and the National Natural Science Foundation of China, respectively. The most prominent journals on the top are Applied Energy and Energies, which indicates that journal reputation and open access are critical considerations for the author’s choice of publication outlet. The high productivity of the major stakeholders in MLARE is due to collaborations and research funding support. The keyword co-occurrence analysis identified four (4) clusters or thematic areas on MLARE, which broadly describe the systems, technologies, tools/technologies, and socio-technical dynamics of MLARE research. Overall, the study showed that ML is critical to the prediction, operation, and optimization of renewable energy technologies (RET) along with the design and development of RE-related materials.Öğe New Insights into the Emerging Trends Research of Machine and Deep Learning Applications in Energy Storage: A Bibliometric Analysis and Publication Trends(Econjournals, 2023) Ajibade, Samuel-Soma M.; Zaidi, Abdelhamid; Al Luhayb, Asamh Saleh M.; Adediran, Anthonia Oluwatosin; Voumik, Liton Chandra; Rabbi, FazleThe publication trends and bibliometric analysis of the research landscape on the applications of machine and deep learning in energy storage (MDLES) research were examined in this study based on published documents in the Elsevier Scopus database between 2012 and 2022. The PRISMA technique employed to identify, screen, and filter related publications on MDLES research recovered 969 documents comprising articles, conference papers, and reviews published in English. The results showed that the publications count on the topic increased from 3 to 385 (or a 12,733.3% increase) along with citations between 2012 and 2022. The high publications and citations rate was ascribed to the MDLES research impact, co-authorships/collaborations, as well as the source title/journals’ reputation, multidisciplinary nature, and research funding. The top/most prolific researcher, institution, country, and funding body on MDLES research are; is Yan Xu, Tsinghua University, China, and the National Natural Science Foundation of China, respectively. Keywords occurrence analysis revealed three clusters or hotspots based on machine learning, digital storage, and Energy Storage. Further analysis of the research landscape showed that MDLES research is currently and largely focused on the application of machine/deep learning for predicting, operating, and optimising energy storage as well as the design of energy storage materials for renewable energy technologies such as wind, and PV solar. However, future research will presumably include a focus on advanced energy materials development, operational systems monitoring and control as well as techno-economic analysis to address challenges associated with energy efficiency analysis, costing of renewable energy electricity pricing, trading, and revenue prediction.Öğe New Insights into the Research Landscape on the Application of Artificial Intelligence in Sustainable Smart Cities: A Bibliometric Mapping and Network Analysis Approach(Econjournals, 2023) Zaidi, Abdelhamid; Ajibade, Samuel-Soma M.; Musa, Majd; Bekun, Festus VictorHumanity’s quest for safe, resilient, and liveable cities has prompted research into the application of computational tools in the design and development of sustainable smart cities. Thus, the application of artificial intelligence in sustainable smart cities (AISC) has become an important research field with numerous publications, citations, and collaborations. However, scholarly works on publication trends and the research landscape on AISC remain lacking. Therefore, this paper examines the current status and future directions of AISC research. The PRISMA approach was selected to identify, screen, and analyse 1,982 publications on AISC from Scopus between 2011 and 2022. Results showed that the number of publications and citations rose from 2 to 470 and 157 to 1,540, respectively. Stakeholder productivity analysis showed that the most prolific author and affiliation are Tan Yigitcanlar (10 publications and 518 citations) and King Abdulaziz University (23 publications and 793 citations), respectively. Productivity was attributed to national interests, research priorities, and national or international funding. The largest funder of AISC research is the National Natural Science Foundation of China (126 publications or 6.357% of the total publications). Keyword co-occurrence and cluster analyses revealed 6 research hotspots on AISC: Digital innovation and technologies; digital infrastructure and intelligent data systems; cognitive computing; smart sustainability; smart energy efficiency; nexus among artificial intelligence, Internet of Things, data analytics and smart cities. Future research would likely focus on the socio-economic, ethical, policy, and technical aspects of the topic. It is envisaged that global scientific interest in AISC research and relevant publications, citations, products, and services will continue to rise in the future.Öğe Quantifying the Dynamic Factors Influencing New-Age Users' Adoption of 5G Using TAM and UTAUT Models in Emerging Country: A Multistage PLS-SEM Approach(Hindawi Limited, 2023) Dadhich, Manish; Rathore, Sumangla; Gyamfi, Bright Akwasi; Ajibade, Samuel-Soma M.; Agozie, Divine Q.Objectives. The 5G has ushered in a new age of life-changing breakthroughs and advancements due to faster speeds, greater bandwidth, and ultra-high expectancy. The study proposes a multistage approach for quantifying the dynamic factors affecting users’ adoption of 5G in emerging countries. Method. This study integrated the technology acceptance model (TAM) and unified theory of acceptance and use of technology (UTAUT) to recommend a comprehensive model that the industry–academia can adopt. In the proposed model, various core hypotheses and subhypotheses were tested by employing 510 5G users of the metro cities of India. An online questionnaire was used to collect the facts, and the data were framed in the conceptual model to test the validation using partial least squares structural equation modeling (PLS-SEM). Results. The findings suggest that users’ perceptions of adopting 5G are overwhelming in that perceived trust was discovered as a mediating enabler between behavioral intention (BI) and selected manifest. Performance expectancy (PE), effort expectancy (EE), social factors (SF), facilitating factors (FF), hedonic motivation (HM), perceived benefits (PB), price value (PV), and habit (HB). Contribution. By identifying key enablers in the suggested model, service providers may better evaluate these aspects, particularly in ensuring reliable infrastructure for 5G service stands. The study is undoubtedly a novel attempt to assist the telecom industry and policymakers in accelerating the adoption of 5G in emerging economies of Asian continents.Öğe A Quantitative Based Research on the Production of Image Captioning(Ismail Saritas, 2023) Ajibade, Samuel-Soma M.; Zaidi, Abdelhamid; Maidin, Siti Sarah; Ishak, Wan Hussain Wan; Adetunla, AdedotunIt is widely recognized that modern systems can discern the context of an image and enrich it with relevant captions through the fusion of computer vision and natural language processing, a technique referred to as 'image caption production.' This article aims to shed light on and analyze various image captioning techniques that have evolved over the past few decades, including the Attention Model, Region-Level Caption Detection, Semantic Content-Based Models, Multimodal Models, and more. The evaluation of these techniques employs diverse criteria such as Precision Rate, Recall Rate, F1 Score, Accuracy Rate, among others, while employing various datasets for comparison. This article offers a comprehensive structural examination of contemporary image captioning methods. Researchers can leverage the insights from this analysis to develop innovative, improved approaches that sidestep the shortcomings of older methods while retaining their beneficial aspects.Öğe A research landscape bibliometric analysis on climate change for last decades: Evidence from applications of machine learning(Elsevier, 2023) Ajibade, Samuel-Soma M.; Zaidi, Abdelhamid; Bekun, Festus Victor; Adediran, Anthonia Oluwatosin; Bassey, Mbiatke AnthonyClimate change (CC) is one of the greatest threats to human health, safety, and the environment. Given its current and future impacts, numerous studies have employed computational tools (e.g., machine learning, ML) to understand, mitigate, and adapt to CC. Therefore, this paper seeks to comprehensively analyze the research/publications landscape on the MLCC research based on published documents from Scopus. The high productivity and research impact of MLCC has produced highly cited works categorized as science, technology, and engineering to the arts, humanities, and social sciences. The most prolific author is Shamsuddin Shahid (based at Universiti Teknologi Malaysia), whereas the Chinese Academy of Sciences is the most productive affiliation on MLCC research. The most influential countries are the United States and China, which is attributed to the funding activities of the National Science Foundation and the National Natural Science Foundation of China (NSFC), respectively. Collaboration through co-authorship in high impact journals such as Remote Sensing was also identified as an important factor in the high rate of productivity among the most active stakeholders researching MLCC topics worldwide. Keyword co-occurrence analysis identified four major research hotspots/themes on MLCC research that describe the ML techniques, potential risky sectors, remote sensing, and sustainable development dynamics of CC. In conclusion, the paper finds that MLCC research has a significant.
