Agriculture plays a vital role in ensuring global food security, yet it faces growing challenges from climate change, resource limitations, and increasing demand. This paper presents an ensemble learning framework that leverages Internet of Things (IoT) sensor data for crop recommendation and plant disease prediction in precision agriculture. Environmental parameters including temperature, humidity, rainfall, soil pH, and nutrient levels are modeled using Random Forest, Neural Networks, and Logistic Regression classifiers. Experimental evaluation on a publicly available dataset shows that Random Forest achieves superior performance, reaching 89.20% accuracy and the highest F1-score, outperforming baseline models in robustness and interpretability. The integration of Apache Spark enables scalable and near real-time analysis, making the approach suitable for practical deployment. By combining ensemble learning with sensor-driven environmental monitoring, the proposed framework supports sustainable, interpretable, and data-driven agricultural decision-making for farmers, researchers, and policymakers.
In the academic environment, students, researchers, professors, and professionals occasionally experience high stress levels due to increasing coursework demands, deadlines, and personal factors, which can lead to burnout and decrease in their academic performance. To address this challenge, we propose a platform based on a Digital Twin (DT) model for student stress management, integrating physiological, self-reported, and contextual data to enable stress monitoring and prediction. The proposed solution includes wearable devices to collect heart rate, heart rate variability, activity, and sleep quality, while a mobile application gathers pre- and post-activity stress levels, workload evaluations, and academic performance metrics. Additionally, contextual data, including academic schedules and deadlines, will be examined as stress related factors. The proposed DT use machine learning algorithms to predict individual stress and to optimize personalized interventions. The system aims to adjust study plans and suggest behavioral changes, in order to prevent high stress levels of the individuals. Initial results reveal that integrating biosignals with academic data, enhances stress prediction accuracy, offering an adaptive tool for improving students’ well-being and academic performance.
The use of literature in foreign language learning has been largely disputed over the last decades as not being necessary or even as being a hindrance for the learners since it makes no contribution to the purpose of learning a language for practical use. However, lately there has been a turn towards using authentic material in the classrooms and literature provides such a resource. But young children and teenagers seem to have lost interest in reading books since they prefer digital media. So, how can a teacher use literary texts without discouraging their students from studying them? Technology has come to help. Multimodal texts and digital educational games have received increasing attention in recent years as research shows that they affect students’ learning and motivation. They stimulate the students’ imagination and promote skills such as problem solving and collaboration. They help students develop multiliteracies such as visual literacy, cultural literacy, information literacy and critical literacy. In this paper we shall focus on the main steps to consider in this process.
In humanities manuscripts have always been used primarily for research and secondary for teaching. Manuscripts usually are catalogued for researchers to be able to find what they need. However, the large number of manuscripts makes it difficult to access the information needed. Also, the fact that most of them can only be accessed in site, makes access to them even more difficult. With the rise of digital humanities a number of digital resources have been made available, so that researchers from all over the world may be able to access manuscripts and use them for their research. In this paper we present a number of these resources to help researchers choose the ones most suitable for them.
As conversational AI systems, like ChatGPT, become embedded in everyday activities such as education, decision-making, and communication, trust between users and these systems is emerging as a critical factor in their sustained effectiveness and acceptance. However, trust is not static; it can degrade when users encounter ambiguous, incorrect, or misaligned responses. While prior research has extensively addressed trust formation and erosion, little is known about how trust can be actively repaired during dialogue. This paper addresses that gap by introducing the concept of trust recalibration – the process through which conversational agents recover user trust after a breakdown in interaction. We analyze four distinct repair strategies (explicit correction, clarification, apology with rephrasing, and meta-cognitive reflection) using simulated ChatGPT dialogues with annotated trust trajectories. Based on this analysis, we propose a lightweight rule-based model for predicting trust drift and recovery, supported by both quantitative metrics and qualitative dialogue evidence. Our results show that timely, context-appropriate repair strategies significantly enhance trust recovery, especially when matched to the domain of interaction. The paper concludes with a trust recalibration flow model and design recommendations for building more transparent, self-aware AI dialogue systems.
