International Journal of Emerging Research in Engineering, Science, and Management
Not a member yet
94 research outputs found
Sort by
Machine Learning–Based Prediction of Organic Solar Cell Performance Using Molecular Descriptors
Get PDFThe performance of Organic Solar Cells (OSCs) is intrinsically linked to the molecular, electronic, and structural properties of donor and acceptor materials. This study employs various machine learning techniques, namely the Generalized Regression Neural Network (GRNN), Support Vector Machine (SVM), and Tree Boost, to predict key performance metrics of OSCs, including power conversion efficiency (PCE), short-circuit current density (JSC), open-circuit voltage (VOC), and fill factor (FF). The models are trained and evaluated using an experimentally reported dataset compiled by Sahu et al. Correlation analysis demonstrates that material characteristics such as polarizability, bandgap, dipole moment, and charge transfer are statistically associated with OSC performance. The predictive performance of the GRNN model is compared with that of the SVM and Tree Boost models, showing consistently lower prediction errors within the considered dataset. In addition, sensitivity analysis is performed to assess the relative importance of the predictor variables and to examine the influence of kernel functions on GRNN performance. The results indicate that machine learning models, particularly GRNN, can serve as effective data-driven tools for predicting the performance of organic solar cells and for supporting computational screening studies
Ensemble Approach for Hypertension Risk Prediction Using Clinical and Demographic Features
Get PDFHypertension, also known as high blood pressure, is a major risk factor for cardiovascular diseases and stroke, and it often progresses silently until severe complications arise. Early detection is therefore essential for timely management and prevention. Traditional screening methods, however, do not always integrate multiple risk factors for accurate and early identification. This study develops a hypertension prediction system using deep learning and ensemble machine-learning techniques based on a dataset containing demographic, clinical, and lifestyle features. A Multi-Layer Perceptron (MLP), Random Forest, and XGBoost were trained and evaluated, with the Random Forest achieving an accuracy of 87.13%, XGBoost 84.50%, and the MLP 76.28%. An ensemble of the three models achieved 94% accuracy, indicating improved stability and predictive capability. While the system performs well, limitations such as possible overfitting and population-specific bias are noted. The study contributes to AI-driven healthcare by demonstrating a practical approach for early hypertension risk prediction. Future work may involve expanding the dataset, incorporating additional clinical indicators, and improving model robustness across diverse populations
Study of Awareness Towards Life Skill Education among Secondary-level Students
Get PDFThe concept of life skills is related to the way of life that emphasises the mutual exchange of knowledge, attitudes, and interpersonal skills in education. Its objective is to develop diverse skills among students and prepare them to face life’s challenges with determination. The World Health Organization has defined life skills as “the positive behaviours and tendencies that enable a person to adapt in day-to-day life.” Life skills are the abilities that enable a person to adapt and exhibit positive behaviour, allowing them to deal effectively with the problems and challenges of daily life. Life is a unique gift. Therefore, by equipping life with various skills, happiness, peace, and prosperity are created. In this research, with the objectives of the study in mind, an analytical examination of life skills among secondary-level students has been conducted. This research study examines the effects of living conditions, gender, and social class on students’ life skills and presents the findings. Future researchers can build upon this, and other factors affecting the research can also be explored
AI-Driven Multimodal Emotion Recognition and Personalized Recommendations Using Power BI
Get PDFMental health challenges demand innovative, non-invasive interventions to reduce stress and enhance emotional stability. Music has long served as a therapeutic medium; however, existing approaches often rely on generic playlists that lack personalization and adaptability to an individual’s psychological state. This paper presents a novel framework that combines webcam-based facial expression analysis with questionnaire-based self-reports to achieve robust emotion detection. The proposed system employs deep learning models to extract emotional cues from visual data, while structured self-assessments provide subjective validation of user states. A fusion mechanism integrates both modalities to enhance the accuracy and reliability of emotion recognition. Based on the detected emotional profile, personalized music recommendations are generated and visualized through interactive Power BI dashboards. This multimodal, AI-driven approach bridges traditional music therapy with modern data analytics, enabling adaptive, accessible, and user-centric mental health support. The experimental results highlight the potential of this method to enhance emotional well-being, alleviate stress, and increase access to personalized therapy
Reducing Carbon Footprints with On-Grid Photovoltaic Systems: A Path to Sustainability
Get PDFThe unrelenting effort to mitigate carbon emissions has gained crucial momentum in establishing a secure and sustainable environment. Significant emphasis is being placed on achieving environmental sustainability and enhancing carbon capture. This study highlights the critical importance of solar photovoltaic (PV) energy systems in addressing environmental concerns and strengthening energy sectors. It specifically focuses on the emergence of connected photovoltaic systems and their potential to supply the energy sector while reducing carbon dioxide emissions. Through the design of a connected photovoltaic system with a maximum operating power of 584 kW under conditions of 1000 W/m² and 50°C, consisting of 1,095 modules covering an area of 2,994 m², the study demonstrated the system’s ability to save between 13,636 and 23,117 tons of carbon dioxide. These results indicate that photovoltaic systems are a sustainable and transformative solution capable of maintaining the energy sector’s balance by 2050. Furthermore, they serve as a pivotal link in promoting environmental enhancement through renewable, inexhaustible energy sources
Re-Envisioning Talent Management in the 5th Industrial Revolution: A Conceptual Framework Integrating Systems and Design Thinking
Get PDFThe 5th Industrial Revolution (5IR) is reshaping the global business landscape by integrating artificial intelligence, robotics, and the Internet of Things with a renewed focus on human-centered innovation. Talent management (TM), traditionally regarded as a human resources function, must re-envision itself within this paradigm. This paper develops a conceptual framework that applies systems thinking and design thinking to talent management in the context of the 5IR, enabling organizations to remain agile, innovative, and resilient. Systems thinking offers a holistic perspective on understanding the interconnections within the talent ecosystem, while design thinking promotes creative, empathetic, and human-centered solutions. Drawing on recent research on coopetition in SMEs, project-based talent development, global talent practices, and digital readiness in the public sector, the framework highlights the importance of upskilling, leadership support, and the responsible adoption of AI. The outcomes suggest that organizations should adopt holistic and adaptive talent management practices to address skills gaps, foster innovation, and maintain a competitive advantage in the rapidly evolving global environment
Contractors’ Selection Criteria and Construction Project Outcome in Rivers State
Get PDFThe building industry plays a leading role in the macroeconomic development of sovereign states, particularly in the provision of essential infrastructure such as bridges, motorways, and other structures that underpin commercial activity. However, the same sector in emerging economies often struggles to deliver projects that fully meet planned performance targets, largely due to inadequate contractor selection procedures. This paper examined the relationship between contractor selection standards and construction project performance outcomes. The survey tool consisted of 29 items on a five-point Likert scale and was administered to 132 officers of the Rivers State Universal Basic Education Board (RSUBEB). Data analysis was conducted using descriptive statistics and Pearson correlation analysis with SPSS V.23. The results revealed a strong positive relationship (r = 0.846; p = 0.000) between the rigor of contractor selection requirements and positive project results. Based on that, the research proposes that standardized evaluation metrics that emphasize financial soundness, technical skills, prior experience, and resource availability should be prioritized as key factors associated with improved construction project performance
Assessment of Heavy Metal Levels in Water Samples Collected from Odugbo River, Benue State, Nigeria
Get PDFDrinking water is essential for life worldwide and is used daily. However, the quality of this drinking water varies from one source to another. In this research, analysis of five heavy metals: Pb, Zn, Cu, Mn, and Cd was carried out using the AAS technique in four water samples꞉: upper river water (L1), middle river water (L2), lower river water (L3), and Bottled water. The results of the study showed that Pb was found in the range of 0.411±0.001 mg/L to 0.852±0.021 mg/L in all the water samples analysed which is above the permissible limits of USEPA (0.015 mg/L), WHO (0.01 mg/L), SON (0.01 mg/L), and NAFDAC (0.01 mg/L) indicating health risk. Report from the four samples indicated the concentrations of Zn to be in the range 0.140±0,003 mg/L to 0.171±0.003 mg/L, which is below the permissible limits of USEPA (5.0 mg/L), WHO (5 mg/L), NAFDAC (5 mg/L), and SON (3.0 mg/L), and hence, no possible health risk. The results of the findings showed that the concentration of Cu is within the range of 0.212±0.027 mg/L to 0.761±0.012 mg/L and is found to be lower when compared to WHO (2.0 mg/L), NAFDAC (1.5 mg/L), USEPA (1.3 mg/L), and SON (1.0 mg/L). Mn ranged from 0.140±0.002 mg/L to 0.162±0.002 mg/L, below the standard that all the regulatory agencies set. Cd was found in the range of 0.200±0.001 mg/L to 0.231±0.231 mg/L and was found to be above all the regulatory agencies. Therefore, there is a need to take proactive action following the results of this research, which showed that concentrations of Pb and Cd in all the water samples analysed were detected above the permissible limits of the regulatory bodies, which is a potential health risk, either short-term or long-term, to the human body. The study further reviewed the fact that the bottled water analysed is of no significant quality compared to the river water
Integration of Artificial Intelligence in Network Technology: A Literature Review
Get PDFIntegrating Artificial Intelligence (AI) and network technology represents a transformative advancement in modern networks’ protection, management, and optimisation. This literature review presents a comprehensive overview of current developments, existing challenges, and future directions for AI applications in computer networking. The primary aim is synthesising recent research to illustrate how AI-driven technologies reshape traditional network models and drive the shift toward more intelligent, autonomous, and resilient infrastructures, particularly in emerging 5G and forthcoming 6G networks. Network systems have evolved from simple analogue designs into complex digital ecosystems that support high-speed communication, intelligent devices, and data-intensive applications. However, this rapid growth has outpaced the capabilities of traditional rule-based network management approaches, highlighting the need for adaptive, real-time solutions. AI through machine learning (ML) and deep learning (DL) offers powerful data processing, pattern recognition, and autonomous decision-making capabilities, positioning it as a key enabler for managing growing complexity, enhancing security, and supporting autonomous operations. A systematic review was employed to ensure methodological rigour, focusing on peer-reviewed journal articles, leading conference papers, and expert analyses related to AI use in network security, administration, and optimisation. Thematic and comparative analyses were conducted to identify key trends, performance indicators, and innovative developments across various network layers, particularly emerging AI paradigms such as dynamic graph learning, federated learning, and explainable AI (XAI). The review finds that AI significantly improves network performance, including enhanced intrusion detection, advanced threat analysis, intelligent traffic routing, predictive maintenance, and autonomous resource allocation. Furthermore, AI is instrumental in enabling the full potential of 5G and future 6G technologies, supporting features like network slicing, ultra-low latency communication, and novel use cases such as real-time remote healthcare and immersive extended reality (XR) experiences. Despite these advancements, several research gaps remain. These include the lack of standardisation, challenges balancing model interpretability with accuracy, real-time explainability, developing lightweight AI models suited for constrained networking hardware, and concerns around privacy and ethical use. This review ultimately underscores the importance of continued interdisciplinary collaboration to ensure responsible, effective, and sustainable integration of AI into networking. As the digital landscape continues to grow, AI will be essential in driving the development of faster, more intelligent, and more secure network environments
Assessing Computer Science Teachers\u27 Competence in Constructing Essay Test Items: A Comparative Study of Lower and Higher Order Thinking Skills in Junior Secondary Schools in Benue State
Get PDFThis study assessed the competence of junior secondary school Computer Science teachers in Benue State, Nigeria, in constructing essay test items based on Bloom’s Taxonomy, comparing the LOTS and HOTS. Adopting a descriptive survey design, the study was guided by two research questions and a hypothesis. The scope targeted junior secondary school Computer Science teachers in the state, and stratified disproportionate random sampling was used to select 105 teachers. Data was collected using the Computer Science Teachers’ Essay Test Item Construction Competency Test (CSTETICCT), a validated 30-item instrument covering all six cognitive levels of Bloom’s Taxonomy. Instrument reliability was confirmed through a pilot test involving 20 respondents, yielding a KR-20 coefficient of 0.85. Descriptive statistics (frequencies, percentages, means, and standard deviations) and visual aids (charts and graphs via Microsoft Excel) were used for data presentation. Inferential statistics, including t-test, ANOVA, and post hoc analysis, were conducted using SPSS Version 20. Findings, among others, revealed that teachers demonstrated high competence in constructing items for lower-order thinking skills (knowledge and comprehension), moderate ability at the application level, and low competence in higher-order thinking skills (analysis, synthesis, and evaluation), these different competency levels in constructing items that assess LOTS and HOTS were found to be significant. The study concludes that while teachers are proficient in evaluating lower-order cognitive skills, there is a notable gap in their ability to develop higher-order assessment items. It recommends continuous professional development, curriculum revision to include specialised Computer Science training, optional certification in assessment design, and mentorship programs to enhance teachers’ assessment competencies across all cognitive levels