International Journal of Recent Technology and Applied Science (IJORTAS)

AR Technology Educational Game for Inspiring Students to Implement Zero Waste Management

2026-04-12T08:18:09+00:00

Alongside Malaysia's population expansion, the amount of waste being thrown away has continuously increased, with the majority of it ending up in landfills. AR bridges the gap between abstract ideas and real-world experiences by allowing students to see and interact with virtual objects and information in the actual world. 5Rs-AG (AR Technology Educational Game for Inspiring Students to Implement Zero Waste Management) app is a mobile application that has AR technology in it to assist target users like students, local communities also UPSI students to learn and as for teachers to use as a learning aid in the learning process in school. The objective of this research is to identify significant elements of creating an effective learning aid by developing an AR mobile game about the 5Rs of zero waste management, develop the prototype in the mobile application AR Game also evaluate the usability of the developed prototype AR Game. The method that is being used is the Evolutionary Prototyping model. The evaluation is conducted using the System Usability Scale (SUS). Random 18 respondents are participated answering the Evaluation Form. From the analysis finding, the mean from all the statements is 3.84 which represents all the respondents are Agree and the SUS Final Score is 71.80 that represents as Good. Thus, using AR technology is the best way for students to learn interactively about waste management.

Explaining Cholesterol-Related Coronary Artery Disease Risk Using Machine Learning and SHAP

2026-04-12T08:18:07+00:00

Coronary Artery Disease (CAD) remains a leading cause of global mortality, with dyslipidemia recognized as a major modifiable risk factor. This study investigates the relationship between serum lipid parameters and CAD using the Z-Alizadeh Sani clinical dataset comprising 303 patients with 55 clinical, biochemical, and electrocardiographic attributes. Logistic Regression (LR) and Random Forest (RF) models were developed to predict CAD status, supported by a standardized preprocessing pipeline, multi-split train–test evaluation (70/30, 80/20, 90/10), and performance assessment using Accuracy, Precision, Recall, F1-Score, and AUC-ROC. SHapley Additive exPlanations (SHAP) were employed to enhance model interpretability and quantify the contribution of lipid-related and clinical features to individual predictions. The RF model consistently outperformed LR across all split configurations, achieving a maximum AUC of 0.96, while LR attained an AUC of 0.90. SHAP analysis revealed that total cholesterol (CHOL) and low-density lipoprotein (LDL) were strong positive predictors of CAD, whereas high-density lipoprotein (HDL) exhibited a protective effect, in line with established cardiovascular pathophysiology. These findings demonstrate that integrating explainable machine learning with routine clinical lipid profiles can provide accurate and transparent decision support for early CAD risk stratification.

Performance Optimisation of Hybrid Renewable Systems for Remote Off-Grid Electrification

2026-04-12T08:18:03+00:00

This research focuses on modelling, simulation and optimization of a HRES for off grid electrification in remote areas of Uganda using solar and wind as the renewable sources, targeting a community of 100 households and 10 medical centers in Rigbo Sub-County, Arua District. Using HOMER Pro software, five configurations were evaluated: solar only, solar and wind, solar with generator, wind with generator, and a combination of solar and wind with generator. Costs, electrical performance and environmental impact of the configurations were compared. Load profiles were developed by estimating a daily consumption of households and medical centers, scaled to total annual load of 189,500-189,581kWh. Results indicate that hybrid systems incorporating a generator, particularly the configuration of solar, wind and generator, outperforms others with the lowest total NPC and the lowest LCOE and no unmet load, while maintaining high renewable fraction and manageable CO2 emission. Future studies should focus on validating these simulation results with empirical data from actual pilot deployments in remote Ugandan villages to account for real-world weather unpredictability. Investigating more dynamic and diverse energy demand models would also provide a deeper understanding of consumption patterns beyond uniform assumptions. Exploring the integration of advanced energy storage technologies and smart grid management could offer ways to further reduce reliance on diesel generators while maintaining system reliability.

Utilization of GIS-Based UAV Systems for Mapping and Monitoring Agricultural Land

2026-04-12T08:18:00+00:00

Bangladesh faces serious challenges in agricultural mapping and monitoring due to urbanization, climate change, and the limitations of manual methods. This research aims to utilize a Geographic Information System (GIS)-based UAV system for efficient and accurate agricultural mapping and monitoring. The system collects multispectral data on vegetation conditions, soil moisture, and crop growth, and identifies areas affected by drought or pest infestations. The UAV is designed to cover large areas difficult for humans to access, with data integrated into GIS for spatial analysis and precision agriculture-based recommendations. The research methodology employed a quantitative approach with experimental methods and GIS spatial analysis. It was conducted from September to December 2025 in three key agricultural districts: Gazipur, Rajshahi, and Khulna. The multirotor UAV was equipped with a multispectral camera, a high-resolution RGB camera, GPS, and autopilot for coordinate accuracy and automated flight path planning. Image acquisition was conducted two to three times during the growing season, supplemented by soil moisture measurements, weather data, visual observations, and respondent interviews for validation. The results demonstrated that the UAV-GIS system was capable of producing accurate maps of vegetation conditions, soil moisture, and crop stress areas. Field findings indicate that the integration of GIS spatial analysis can detect crop conditions with an accuracy of up to 92%, surpassing conventional methods, which only reach 70%. Furthermore, operational efficiency has increased, with work time reduced from 10 hours to just 2 hours per hectare, and costs reduced from $25 to $15. This system aligns with previous studies on the effectiveness of UAVs and GIS in monitoring hard-to-reach areas, supporting precision agriculture practices, and improving productivity and sustainability. Further research could explore fixed-wing UAVs for larger areas, the integration of LiDAR or hyperspectral sensors, the development of AI algorithms for predicting crop stress and disease, and sustainable business models for UAV-GIS adoption in developing countries.

A Framework for Sovereign AI Governance and Economic Growth in Cameroon

2026-04-12T08:17:58+00:00

Artificial Intelligence is no longer just a trend in technology. It has become a structural force that determines national competitiveness and economic resilience. While many advanced nations are already integrating AI into their core systems, most Sub-Saharan African states still lack the institutional frameworks needed to turn these innovations into sustainable development. This paper argues that Cameroon should not view AI simply as modernization. Instead, it must be treated as a sovereign strategy built on institutional economics, deliberate governance, and a solid blended finance architecture. Using comparative policy analysis and digital infrastructure modeling, the study proposes a three-layer framework tailored to Cameroon’s specific political economy. This model draws on international standards from the OECD, UNESCO, and the African Union, alongside the NIST Risk Management Framework. The findings show that with coordinated reform, AI could boost Cameroon’s long-term productivity by 1.5% to 2.8% annually. To fund this transition, the paper introduces a blended finance structure designed to attract multilateral banks and private venture capital. Further research is needed to explore the longitudinal impact of these AI deployments on local labor markets and the creation of indigenous datasets that reflect Cameroon’s unique linguistic diversity. Ultimately, this work contributes to the growing body of research on digital sovereignty and the political economy of AI in frontier markets.