We are considering a facet of precision agriculture that concentrates on plant-driven crop management. By monitoring soil, crop and climate in a field and providing a decision support system that is able to learn, it is possible to deliver treatments, such as irrigation, fertilizer and pesticide application, for specific parts of a field in real time and proactively. In this context, we have applied machine learning techniques to automatically extract new knowledge in the form of generalized decision rules towards the best administration of natural resources like water. The machine learning application model suggested in this paper is based on an inductive and iterative process of discovering knowledge on the basis of which, patterns and associations having arisen initially are re-examined to expand the pre-existing knowledge. The result of this study was the creation of an effective set of decision rules used to predict the plants' state and the prevention of unpleasant impacts from the water stress in plants.

Smart city middleware serves as a foundational tool in the evolution of urban digitalization, acting as an intermediary software layer that simplifies the development, deployment, and management of applications tailored for smart urban environments. However, the development of effective middleware for smart cities is challenging. The present research embarks on a comprehensive exploration of the smart city middleware landscape, unraveling the intricacies of its development and the challenges faced therein. Rooted in the assessment of 20 distinct middleware solutions, our study highlights the pivotal technologies, features and functionalities that are imperative for a middleware to effectively support a city’s digital transformation. The functional and non-functional requirements form the nucleus of our evaluation. We also explore the architectural styles pivotal to middleware development and the programming paradigms shaping smart city application development. Our study highlights challenges in using middleware for smart city applications, such as interoperability, scalability, security amidst big data, context management, reliability, quality of service, energy efficiency, and compliance with technological standards and regulations. Based on the detailed analysis, we propose a conceptual framework for smart city middleware, shaped by the challenges and requirements identified in existing literature and middleware solutions. This framework is designed to reflect the diverse demands and complexities of urban digital transformation, and guide smart city middleware development accordingly. As a result, this research stands as a reference study for software developers, urban planners, and researchers, outlining the current state and future directions in the domain of smart city middleware.

Mild cognitive impairment (MCI) is an indicative precursor of Alzheimer’s disease and its early detection is critical to restrain further cognitive deterioration through preventive measures. In this context, the capacity of serious games combined with machine learning for MCI detection is examined. In particular, a custom methodology is proposed, which consists of a series of steps to train and evaluate classification models that could discriminate healthy from cognitive impaired individuals on the basis of game performance and other subjective data. Such data were collected during a pilot evaluation study of a gaming platform, called COGNIPLAT, with 10 seniors. An exploratory analysis of the data is performed to assess feature selection, model overfitting, optimization techniques and classification performance using several machine learning algorithms and standard evaluation metrics. A production level model is also trained to deal with the issue of data leakage while delivering a high detection performance (92.14% accuracy, 93.4% sensitivity and 90% specificity) based on the Gaussian Naive Bayes classifier. This preliminary study provides initial evidence that serious games combined with machine learning methods could potentially serve as a complementary or an alternative tool to the traditional cognitive screening processes.