International Journal of Electrical and Computer Engineering Research

Development of a Web Platform for Precision Agriculture Optimization

2025-08-27T20:16:08+03:00

This study presents the development of a low-cost web-based platform designed to improve precision agriculture in the sugarcane sector through real-time monitoring of key environmental variables. The proposed system aims to address the technological gap in rural agricultural settings by integrating accessible and open-source technologies. The methodology involved the use of temperature, humidity, and rainfall sensors connected to an Arduino microcontroller, which transmits the collected data via HTTP to a MySQL database. A web interface, developed using HTML, CSS, and PHP, enables users to remotely visualize environmental conditions through graphical and numerical formats. The platform was implemented and tested in a sugarcane cultivation environment to evaluate its performance in terms of responsiveness, stability, and usability. Results from field testing indicated a latency of less than three seconds in data transmission, with an automatic update frequency of approximately one minute. Additionally, a significant reduction in data retrieval time was observed, along with improved accuracy in decision-making due to the real-time visualization of critical parameters. The entire solution was developed with cost efficiency in mind, reaching an estimated implementation cost of approximately $500, significantly lower than traditional commercial systems. The proposed platform not only automates data acquisition and visualization but also lays the foundation for future integration with artificial intelligence algorithms to enable predictive analysis and advanced decision support. This system offers a scalable, adaptable, and affordable tool to support small and medium-sized producers in rural areas.

Machine Learning-Based Stroke Prediction with Efficient Feature Importance Analysis

2025-06-11T21:29:51+03:00

A stroke represents a critical neurological and vascular emergency that occurs when blood supply to the brain becomes interrupted or reduced, triggering a complex cascade of events that lead to ischemic injury, oxygen deprivation, and ultimately, neuronal death. Advanced artificial intelligence and machine learning algorithms have revolutionized stroke prediction and diagnosis by analysing complex medical imaging data, patient histories, and clinical parameters with remarkable accuracy, enabling healthcare providers to make faster and more precise diagnostic decisions while identifying high-risk patients before stroke occurrence through pattern recognition in large datasets. This research paper explores the application of machine learning in stroke prediction, focusing on the identification of key risk factors. By utilizing a comprehensive dataset and employing a range of machine learning models, including logistic regression, decision trees, random forests, support vector machines, K-nearest neighbours, and gradient boosting, the study aims to uncover significant predictors of stroke. The primary objective is not to outperform existing models, but to gain a deeper understanding of feature importance in stroke risk assessment. Through a multifaceted approach to feature importance analysis, including built-in metrics for tree-based models, coefficient analysis for linear models, and permutation importance for other algorithms, the research identifies the most influential factors in stroke prediction. The findings of this study can contribute to improved stroke prevention and early detection by providing clinicians with interpretable, AI-assisted insights for informed decision-making.

Truth Matters: Generative AI as Muse or Tool in the Research Process

2025-08-27T16:14:24+03:00

The integration of generative artificial intelligence (AI) into research marks both a provocation and an inflection point. While gains in productivity and access draw attention, a deeper transformation is underway: how knowledge is conceptualized, mediated, and validated amid systems that simulate understanding without possessing it. If current trends hold, AI will amplify existing dynamics in scholarly communication. Publication volume may rise, but trust could decline. Conventional markers of originality and rigor may destabilize—not through automation alone, but through shifting norms around authorship, evaluation, and epistemic authority. This paper argues that AI is neither just a tool nor merely a muse, but a structural participant in research — shaping inquiry through fluent simulation but without understanding. A cognitive map is introduced to model how researchers interact with AI across phases of the research process, alternating between instrumental and generative uses. Generative systems can assist and accelerate scholarly work, but their role must be framed within a broader account of intellectual labor and meaning-making. Confusing fluency for insight risks eroding core scholarly practices. Implications extend to pedagogy, authorship policy, and the design of AI-aware research infrastructure. Ultimately, scholarship in the age of AI will depend as much on critical literacy as on technical fluency. AI is not merely a tool of transformation but a mirror—reflecting the values and assumptions of the communities that create and use it.