Generative artificial intelligence (AI) is transforming the learning and teaching landscape, and large language models, such as ChatGPT, Gemini, or Copilot, are demonstrating their outstanding ability to hold conversations and generate relevant content. However, given their probabilistic nature, it is currently not possible to trust completely in their academic performance. A detailed comparison of the accuracy of two AI chatbots, ChatGPT-4o and Gemini 1.5 Pro is presented by measuring their ability to correctly answer multiple-choice questions of standard undergraduate physics questionnaires. A total sample of 790 questions was analyzed, covering 13 mechanics' themes, from units and measurements to gravitation. Each chatbot was given the same prompt and was asked to solve each question. Their answers were compared to the correct answers, and an accuracy indicator was derived for each chatbot. In partial agreement with similar studies, it was found that ChatGPT achieved an overall accuracy of only 58 (±7) points (on a 0–100 scale), while Gemini achieved 79 (±6), which represents a 36% improvement. An analysis of variances proved this difference to be significant. The stability of ChatGPT was also tested through different runs, yielding basically the same performance. Its average accuracy may vary up to 11 points for a given theme. On the other hand, ChatGPT running with the Wolfram Alpha plugin did not achieve a systematic improvement, and its average accuracy may vary up to 17 points for a given theme. A PhysicsGPT by pulsr.co.uk from the OpenAI gallery was also tested, and it only achieved an overall accuracy of 57. When using these AI chatbots to solve multiple-choice questions in undergraduate physics topics requiring mathematical procedures, teachers and students should take these results as a warning about their current lack of precision and potential misleadingness.

The Coronavirus disease 2019 (COVID-19) pandemic has presented unprecedented challenges to global health-care systems, urgently calling for innovative diagnostic solutions. This paper introduces the Fully Automatic Detection of Covid-19 cases in medical Images of the Lung (FADCIL) system, a cutting-edge deep learning framework designed for rapid and accurate COVID-19 diagnosis from chest computed tomography (CT) images. By leveraging an architecture based on YOLO and 3D U-Net, FADCIL excels in identifying and quantifying lung injuries attributable to COVID-19, distinguishing them from other pathologies. In real-world clinical environments, FADCIL achieves a DICE coefficient above 0.82, highlighting its robust performance and clinical relevance. FADCIL also enhances the reliability of COVID-19 assessment, empowering healthcare professionals to make informed decisions and effectively manage patient care. Thus, this paper outlines the FADCIL architecture and presents an in-depth analysis of quantitative and qualitative evaluation results derived from a novel dataset comprising over 1000 CT scans. Furthermore, we provide access to the FADCIL’s source code for public use.

This research paper describes the factors that contribute to the academic success of university students who receive scholarships due to their outstanding performance in high school, along with a track record of social impact and leadership activities, despite their disadvantaged economic status. The data analysis encompasses information from 2014 to 2023 for a sample of 1,796 students at Tecnologico de Monterrey, with over 60% enrolled in engineering programs. This study examines the factors that positively impact the academic performance of students enrolled in the “Leaders of Tomorrow” scholarship program. The most relevant factors are participation in student group activities, international experiences, community activities, and projects related to technological development or research. Additionally, certain demographic factors, such as not being the first family member to attend university, younger age, coming from urban areas, proximity to the university campus, and female gender, also had a positive impact on academic results. It was found that previous work experiences, sports or cultural activities improve academic performance when properly balanced with the time dedicated to the academic study. Furthermore, the scope of student projects in high school, participation in leadership activities or in academic contests were not relevant to the university academic performance. Understanding the diversity of factors that contribute to academic success will enable more effective support, and the implementation of timely interventions aimed at maximizing the educational opportunities of these students.

International audience

The application of machine learning to agriculture is currently experiencing a "surge of interest" from the academic community as well as practitioners from industry. This increased attention has produced a number of differing approaches that use varying machine learning frameworks. It is arguable that Bayesian Networks are particularly suited to agricultural research due to their ability to reason with incomplete information and incorporate new information. Bayesian Networks are currently underrepresented in the machine learning applied to agriculture research literature, and to date there are no survey papers that currently centralize the state of the art. The aim of this paper is rectify the lack of a survey paper in this area by providing a self-contained resource that will: centralize the current state of the art, document the historical progression of Bayesian Networks in agriculture and indicate possible future lines of research as well as providing an introduction to Bayesian Networks for researchers who are new to the area.

Graph-based semi-supervised learning (SSL) provides a powerful framework for the modeling of manifold structures in high-dimensional spaces. Additionally, graph representation is effective for the propagation of the few initial labels existing in training data. Graph-based SSL requires robust graphs as input for an accurate data mining task, such as classification. In contrast to most graph construction methods, which ignore the labeled instances available in SSL scenarios, a previous study proposed a graph-construction method, named GBILI, to exploit the informativeness conveyed by such instances available in a semi-supervised classification domain. Here, we have improved the method proposing an optimized algorithm referred to as Robust Graph that Considers Labeled Instances (RGCLI) for the generation of more robust graphs. The contributions of this paper are threefold: i) reduction of GBILI time complexity from quadratic to O(nklogn). This enhancement allows addressing large datasets; ii) demonstration of RGCLI mathematical properties, proving the constructed graph is an optimal graph to model the smoothness assumption of SSL; and iii) evaluation of the efficacy of the proposed approach in a comprehensive semi-supervised classification scenario with several datasets, including an image segmentation task, which needs a large graph to represent the image. Such experiments show the use of labeled vertices in the graph construction process improves the graph topology, hence, the learning task in which it will be employed.

Link prediction is a “hot topic” in network analysis and has been largely used for friendship recommendation in social networks. With the increased use of location-based services, it is possible to improve the accuracy of link prediction methods by using the mobility of users. The majority of the link prediction methods focus on the importance of location for their visitors, disregarding the strength of relationships existing between these visitors. We, therefore, propose three new methods for friendship prediction by combining, efficiently, social and mobility patterns of users in location-based social networks (LBSNs). Experiments conducted on real-world datasets demonstrate that our proposals achieve a competitive performance with methods from the literature and, in most of the cases, outperform them. Moreover, our proposals use less computational resources by reducing considerably the number of irrelevant predictions, making the link prediction task more efficient and applicable for real world applications.

Many real-world domains are relational in nature since they consist of a set of objects related to each other in complex ways. However, there are also flat data sets and if we want to apply graph-based algorithms, it is necessary to construct a graph from this data. This paper aims to: i) increase the exploration of graph-based algorithms and ii) proposes new techniques for graph construction from flat data. Our proposal focuses on constructing graphs using link prediction measures for predicting the existence of links between entities from an initial graph. Starting from a basic graph structure such as a minimum spanning tree, we apply a link prediction measure to add new edges in the graph. The link prediction measures considered here are based on structural similarity of the graph that improves the graph connectivity. We evaluate our proposal for graph construction in supervised and semi-supervised classification and we confirm the graphs achieve better accuracy.

The multilevel graph partitioning strategy aims to reduce the computational cost of the partitioning algorithm by applying it on a coarsened version of the original graph. This strategy is very useful when large-scale networks are analyzed. To improve the multilevel solution, refinement algorithms have been used in the uncorsening phase. Typical refinement algorithms exploit network properties, for example minimum cut or modularity, but they do not exploit features from domain specific networks. For instance, in social networks partitions with high clustering coefficient or similarity between vertices indicate a better solution. In this paper, we propose a refinement algorithm (RSim) which is based on neighborhood similarity. We compare RSim with: 1. two algorithms from the literature and 2. one baseline strategy, on twelve real networks. Results indicate that RSim is competitive with methods evaluated for general domains, but for social networks it surpasses the competing refinement algorithms.

In recent years, different methods based on kernels have been used with success in a variety of tasks such as classification. However, in the typical use of these methods, the choice of the optimal kernel is crucial to improve the performance of a specific task. So, instead of selecting a single kernel, multiple kernel learning (MKL) has been proposed which uses a combination of kernels, where the weight of each kernel is optimized in the training stage. MKL methods use kernels in linear, nonlinear or data-dependent combinations. Methods based on MKL have performed better than methods using a single kernel such as the Support Vector Machine (SVM). In this article, we propose a new MKL method, which is based on a local (data dependent) and nonlinear combination of different kernels using a gating model for selecting the appropriate kernel function. We call our proposal as localized nonlinear multiple kernel learning (LNLMKL). In our experiments for binary microarray classification, different kernels were used in SVM and different kernels combinations were used for our proposal and for the other MKL methods. Finally, we report the results of these experiments using eight high-dimensional microarray data sets demonstrating that our proposal have performed better than the other methods analyzed.