Next Issue
Volume 10, April
Previous Issue
Volume 10, February
 
 

Data, Volume 10, Issue 3 (March 2025) – 14 articles

Cover Story (view full-size image): Forest ecosystems are important for biodiversity conservation, climate regulation, soil and water protection, recreation, and the provision of raw materials. Information on the species composition of forests is essential for environmental, monitoring, and conservation tasks. We present a large dataset of field data on the forest type and tree species composition collected in 934 accurately georeferenced plots located in Italy, representing a wide range of ecological and silvicultural conditions. They were collected as ground truth data for the development of automatic classification models based on hyperspectral satellite data. The dataset may be of interest to researchers studying forest biodiversity and for analyzing the spectral response of vegetation for remote sensing applications. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
10 pages, 2466 KiB  
Data Descriptor
Analysis of Minerals Using Handheld Laser-Induced Breakdown Spectroscopy Technology
by Naila Mezoued, Cécile Fabre, Jean Cauzid, YongHwi Kim and Marjolène Jatteau
Data 2025, 10(3), 40; https://doi.org/10.3390/data10030040 - 20 Mar 2025
Viewed by 724
Abstract
Laser-induced breakdown spectroscopy (LIBS), a rapid and versatile analytical technique, is becoming increasingly widespread within the geoscience community. Suitable for fieldwork analyses using handheld analyzers, the elemental composition of a sample is revealed by generating plasma using a high-energy laser, providing a practical [...] Read more.
Laser-induced breakdown spectroscopy (LIBS), a rapid and versatile analytical technique, is becoming increasingly widespread within the geoscience community. Suitable for fieldwork analyses using handheld analyzers, the elemental composition of a sample is revealed by generating plasma using a high-energy laser, providing a practical solution to numerous geological challenges, including identifying and discriminating between different mineral phases. This data paper presents over 12,000 reference mineral spectra acquired using a handheld LIBS analyzer (© SciAps), including those of silicates (e.g., beryl, quartz, micas, spodumene, vesuvianite, etc.), carbonates (e.g., dolomite, magnesite, aragonite), phosphates (e.g., amblygonite, apatite, topaz), oxides (e.g., hematite, magnetite, rutile, chromite, wolframite), sulfates (e.g., baryte, gypsum), sulfides (e.g., chalcopyrite, pyrite, pyrrhotite), halides (e.g., fluorite), and native elements (e.g., sulfur and copper). The datasets were collected from 170 pure mineral samples in the form of crystals, powders, and rock specimens, during three research projects: NEXT, Labex Ressources 21, and ARTeMIS. The extensive spectral range covered by the analyzer spectrometers (190–950 nm) allowed for the detection of both major (>1 wt.%) and trace (<1 wt.%) elements, recording a unique spectral signature for each mineral. Mineral spectra can serve as reference data to (i) identify relevant emission lines and spectral ranges for specific minerals, (ii) be compared to unknown LIBS spectra for mineral identification, or (iii) constitute input data for machine learning algorithms. Full article
Show Figures

Figure 1

30 pages, 5472 KiB  
Data Descriptor
The 1688 Sannio–Matese Earthquake: A Dataset of Environmental Effects Based on the ESI-07 Scale
by Angelica Capozzoli, Valeria Paoletti, Sabina Porfido, Alessandro Maria Michetti and Rosa Nappi
Data 2025, 10(3), 39; https://doi.org/10.3390/data10030039 - 19 Mar 2025
Viewed by 913
Abstract
The 1688 Sannio–Matese earthquake, with a macroseismically derived magnitude of Mw = 7 and an epicentral intensity of IMCS = XI, had a deep impact on Southern Italy, causing thousands of casualties, extensive damage and significant environmental effects (EEEs) in the [...] Read more.
The 1688 Sannio–Matese earthquake, with a macroseismically derived magnitude of Mw = 7 and an epicentral intensity of IMCS = XI, had a deep impact on Southern Italy, causing thousands of casualties, extensive damage and significant environmental effects (EEEs) in the epicentral area. Despite a comprehensive knowledge of its economic and social impacts, information regarding the earthquake’s environmental effects remains poorly studied and far from complete, hindering accurate intensity calculations by the Environmental Seismic Intensity Scale (ESI-07). This study aims to address this knowledge gap by compiling a thorough dataset of the EEEs induced by the earthquake. By consulting over one hundred historical, geological and scientific reports, we have collected and classified, using the ESI-07 scale, its primary and secondary EEEs, most of which were previously undocumented in the literature. We verified the historical sources regarding some of these effects through reconnaissance field mapping. Analysis of the obtained dataset reveals some primary effects (surface faulting) and extensive secondary effects, such as slope movements, ground cracks, hydrological anomalies, liquefaction and gas exhalation, which affected numerous towns. These findings enabled us to reassess the Sannio earthquake intensity, considering its environmental impact and comparing traditional macroseismic scales with the ESI-07. Our analysis allowed us to provide an epicentral intensity ESI of I = X, one degree lower than the published IMCS = XI. This study highlights the importance of combining traditional scales with the ESI-07 for more accurate hazard assessments. The macroseismic revision provides valuable insights for seismic hazard evaluation and land-use planning in the Sannio–Matese region, especially considering the distribution of the secondary effects. Full article
Show Figures

Figure 1

14 pages, 2091 KiB  
Data Descriptor
Historical Hourly Information of Four European Wind Farms for Wind Energy Forecasting and Maintenance
by Javier Sánchez-Soriano, Pedro Jose Paniagua-Falo and Carlos Quiterio Gómez Muñoz
Data 2025, 10(3), 38; https://doi.org/10.3390/data10030038 - 19 Mar 2025
Viewed by 470
Abstract
For an electric company, having an accurate forecast of the expected electrical production and maintenance from its wind farms is crucial. This information is essential for operating in various existing markets, such as the Iberian Energy Market Operator—Spanish Hub (OMIE in its Spanish [...] Read more.
For an electric company, having an accurate forecast of the expected electrical production and maintenance from its wind farms is crucial. This information is essential for operating in various existing markets, such as the Iberian Energy Market Operator—Spanish Hub (OMIE in its Spanish acronym), the Portuguese Hub (OMIP in its Spanish acronym), and the Iberian electricity market between the Kingdom of Spain and the Portuguese Republic (MIBEL in its Spanish acronym), among others. The accuracy of these forecasts is vital for estimating the costs and benefits of handling electricity. This article explains the process of creating the complete dataset, which includes the acquisition of the hourly information of four European wind farms as well as a description of the structure and content of the dataset, which amounts to 2 years of hourly information. The wind farms are in three countries: Auvergne-Rhône-Alpes (France), Aragon (Spain), and the Piemonte region (Italy). The dataset was built and validated following the CRISP-DM methodology, ensuring a structured and replicable approach to data processing and preparation. To confirm its reliability, the dataset was tested using a basic predictive model, demonstrating its suitability for wind energy forecasting and maintenance optimization. The dataset presented is available and accessible for improving the forecasting and management of wind farms, especially for the detection of faults and the elaboration of a preventive maintenance plan. Full article
Show Figures

Figure 1

15 pages, 1302 KiB  
Data Descriptor
Experimental Parametric Forecast of Solar Energy over Time: Sample Data Descriptor
by Fernando Venâncio Mucomole, Carlos Augusto Santos Silva and Lourenço Lázaro Magaia
Data 2025, 10(3), 37; https://doi.org/10.3390/data10030037 - 17 Mar 2025
Viewed by 481
Abstract
Variations in solar energy when it reaches the Earth impact the production of photovoltaic (PV) solar plants and, in turn, the dynamics of clean energy expansion. This incentivizes the objective of experimentally forecasting solar energy by parametric models, the results of which are [...] Read more.
Variations in solar energy when it reaches the Earth impact the production of photovoltaic (PV) solar plants and, in turn, the dynamics of clean energy expansion. This incentivizes the objective of experimentally forecasting solar energy by parametric models, the results of which are then refined by machine learning methods (MLMs). To estimate solar energy, parametric models consider all atmospheric, climatic, geographic, and spatiotemporal factors that influence decreases in solar energy. In this study, data on ozone, evenly mixed gases, water vapor, aerosols, and solar radiation were gathered throughout the year in the mid-north area of Mozambique. The results show that the calculated solar energy was close to the theoretical solar energy under a clear sky. When paired with MLMs, the clear-sky index had a correlational order of 0.98, with most full-sun days having intermediate and clear-sky types. This suggests the potential of this area for PV use, with high correlation and regression coefficients in the range of 0.86 and 0.89 and a measurement error in the range of 0.25. We conclude that evenly mixed gases and the ozone layer have considerable influence on transmittance. However, the parametrically forecasted solar energy is close to the energy forecasted by the theoretical model. By adjusting the local characteristics, the model can be used in diverse contexts to increase PV plants’ electrical power output efficiency. Full article
(This article belongs to the Topic Smart Energy Systems, 2nd Edition)
Show Figures

Figure 1

28 pages, 68080 KiB  
Article
KRID: A Large-Scale Nationwide Korean Road Infrastructure Dataset for Comprehensive Road Facility Recognition
by Hyeongbok Kim, Eunbi Kim, Sanghoon Ahn, Beomjin Kim, Sung Jin Kim, Tae Kyung Sung, Lingling Zhao, Xiaohong Su and Gilmu Dong
Data 2025, 10(3), 36; https://doi.org/10.3390/data10030036 - 14 Mar 2025
Viewed by 763
Abstract
Comprehensive datasets are crucial for developing advanced AI solutions in road infrastructure, yet most existing resources focus narrowly on vehicles or a limited set of object categories. To address this gap, we introduce the Korean Road Infrastructure Dataset (KRID), a large-scale dataset designed [...] Read more.
Comprehensive datasets are crucial for developing advanced AI solutions in road infrastructure, yet most existing resources focus narrowly on vehicles or a limited set of object categories. To address this gap, we introduce the Korean Road Infrastructure Dataset (KRID), a large-scale dataset designed for real-world road maintenance and safety applications. Our dataset covers highways, national roads, and local roads in both city and non-city areas, comprising 34 distinct types of road infrastructure—from common elements (e.g., traffic signals, gaze-directed poles) to specialized structures (e.g., tunnels, guardrails). Each instance is annotated with either bounding boxes or polygon segmentation masks under stringent quality control and privacy protocols. To demonstrate the utility of this resource, we conducted object detection and segmentation experiments using YOLO-based models, focusing on guardrail damage detection and traffic sign recognition. Preliminary results confirm its suitability for complex, safety-critical scenarios in intelligent transportation systems. Our main contributions include: (1) a broader range of infrastructure classes than conventional “driving perception” datasets, (2) high-resolution, privacy-compliant annotations across diverse road conditions, and (3) open-access availability through AI Hub and GitHub. By highlighting critical yet often overlooked infrastructure elements, this dataset paves the way for AI-driven maintenance workflows, hazard detection, and further innovations in road safety. Full article
Show Figures

Figure 1

14 pages, 3207 KiB  
Data Descriptor
A Comprehensive Indoor Environment Dataset from Single-Family Houses in the US
by Sheik Murad Hassan Anik, Xinghua Gao and Na Meng
Data 2025, 10(3), 35; https://doi.org/10.3390/data10030035 - 5 Mar 2025
Viewed by 2273
Abstract
The paper describes a dataset comprising indoor environmental factors such as temperature, humidity, air quality, and noise levels. The data were collected from 10 sensing devices installed in various locations within three single-family houses in Virginia, USA. The objective of the data collection [...] Read more.
The paper describes a dataset comprising indoor environmental factors such as temperature, humidity, air quality, and noise levels. The data were collected from 10 sensing devices installed in various locations within three single-family houses in Virginia, USA. The objective of the data collection was to study the indoor environmental conditions of the houses over time. The data were collected at a frequency of one record per minute for a year, combining to a total over 2.5 million records. The paper provides actual floor plans with sensor placements to aid researchers and practitioners in creating reliable building performance models. The techniques used to collect and verify the data are also explained in the paper. The resulting dataset can be employed to enhance models for building energy consumption, occupant behavior, predictive maintenance, and other relevant purposes. Full article
Show Figures

Figure 1

7 pages, 407 KiB  
Data Descriptor
Draft Genome Sequence Data of the Ensifer sp. P24N7, a Symbiotic Bacteria Isolated from Nodules of Phaseolus vulgaris Grown in Mining Tailings from Huautla, Morelos, Mexico
by José Augusto Ramírez-Trujillo, Maria Guadalupe Castillo-Texta, Mario Ramírez-Yáñez and Ramón Suárez-Rodríguez
Data 2025, 10(3), 34; https://doi.org/10.3390/data10030034 - 27 Feb 2025
Viewed by 763
Abstract
In this work, we report the draft genome sequence of Ensifer sp. P24N7, a symbiotic nitrogen-fixing bacterium isolated from nodules of Phaseolus vulgaris var. Negro Jamapa was planted in pots that contained mining tailings from Huautla, Morelos, México. The genomic DNA was sequenced [...] Read more.
In this work, we report the draft genome sequence of Ensifer sp. P24N7, a symbiotic nitrogen-fixing bacterium isolated from nodules of Phaseolus vulgaris var. Negro Jamapa was planted in pots that contained mining tailings from Huautla, Morelos, México. The genomic DNA was sequenced by an Illumina NovaSeq 6000 using the 250 bp paired-end protocol obtaining 1,188,899 reads. An assembly generated with SPAdes v. 3.15.4 resulted in a genome length of 7,165,722 bp composed of 181 contigs with a N50 of 323,467 bp, a coverage of 76X, and a GC content of 61.96%. The genome was annotated with the NCBI Prokaryotic Genome Annotation Pipeline and contains 6631 protein-coding sequences, 3 complete rRNAs, 52 tRNAs, and 4 non-coding RNAs. The Ensifer sp. P24N7 genome has 59 genes related to heavy metal tolerance predicted by RAST server. These data may be useful to the scientific community because they can be used as a reference for other works related to heavy metals, including works in Huautla, Morelos. Full article
(This article belongs to the Special Issue Benchmarking Datasets in Bioinformatics, 2nd Edition)
Show Figures

Figure 1

15 pages, 838 KiB  
Article
Data Quality Tools to Enhance a Network Anomaly Detection Benchmark
by José Camacho and Rafael A. Rodríguez-Gómez
Data 2025, 10(3), 33; https://doi.org/10.3390/data10030033 - 25 Feb 2025
Viewed by 763
Abstract
Network traffic datasets are essential for the construction of traffic models, often using machine learning (ML) techniques. Among other applications, these models can be employed to solve complex optimization problems or to identify anomalous behaviors, i.e., behaviors that deviate from the established model. [...] Read more.
Network traffic datasets are essential for the construction of traffic models, often using machine learning (ML) techniques. Among other applications, these models can be employed to solve complex optimization problems or to identify anomalous behaviors, i.e., behaviors that deviate from the established model. However, the performance of the ML model depends, among other factors, on the quality of the data used to train it. Benchmark datasets, with a profound impact on research findings, are often assumed to be of good quality by default. In this paper, we derive four variants of a benchmark dataset in network anomaly detection (UGR’16, a flow-based real-world traffic dataset designed for anomaly detection), and show that the choice among variants has a larger impact on model performance than the ML technique used to build the model. To analyze this phenomenon, we propose a methodology to investigate the causes of these differences and to assess the quality of the data labeling. Our results underline the importance of paying more attention to data quality assessment in network anomaly detection. Full article
Show Figures

Figure 1

7 pages, 1353 KiB  
Data Descriptor
Spatial Dataset of Climate Robust and High-Yield Agricultural Areas in Brandenburg: Results of a Classification Framework Using Bio-Economic Climate Simulations
by Hannah Jona von Czettritz, Sandra Uthes, Johannes Schuler, Kurt-Christian Kersebaum and Peter Zander
Data 2025, 10(3), 32; https://doi.org/10.3390/data10030032 - 25 Feb 2025
Viewed by 491
Abstract
Coherent spatial data are crucial for informed land use and regional planning decisions, particularly in the context of securing a crisis-proof food supply and adapting to climate change. This dataset provides spatial information on climate-robust and high-yield agricultural arable land in Brandenburg, Germany, [...] Read more.
Coherent spatial data are crucial for informed land use and regional planning decisions, particularly in the context of securing a crisis-proof food supply and adapting to climate change. This dataset provides spatial information on climate-robust and high-yield agricultural arable land in Brandenburg, Germany, based on the results of a classification using bio-economic climate simulations. The dataset is intended to support regional planning and policy makers in zoning decisions (e.g., photovoltaic power plants) by identifying climate-robust arable land with high current and stable future production potential that should be reserved for agricultural use. The classification method used to generate the dataset includes a wide range of indicators, including established approaches, such as a soil quality index, drought, water, and wind erosion risk, as well as a dynamic approach, using bio-economic simulations, which determine the production potential under future climate scenarios. The dataset is a valuable resource for spatial planning and climate change adaptation, contributing to long-term food security especially in dry areas such as the state of Brandenburg facing increased production risk under future climatic conditions, thereby serving globally as an example for land use planning challenges related to climate change. Full article
(This article belongs to the Section Spatial Data Science and Digital Earth)
Show Figures

Figure 1

16 pages, 7115 KiB  
Article
Using Weather Data for Improved Analysis of Vehicle Energy Efficiency
by Reno Filla
Data 2025, 10(3), 31; https://doi.org/10.3390/data10030031 - 24 Feb 2025
Viewed by 552
Abstract
In moving vehicles, the dominating energy losses are due to interactions with the environment: air resistance and rolling resistance. It is known that weather has a significant impact, yet there is a lack of literature showing how the wealth of openly available data [...] Read more.
In moving vehicles, the dominating energy losses are due to interactions with the environment: air resistance and rolling resistance. It is known that weather has a significant impact, yet there is a lack of literature showing how the wealth of openly available data from professional weather observations can be used in this context. This article will give an overview of how such data are structured and how they can be accessed in order to augment logs gained during vehicle operation or simulated trips. Two efficient algorithms for such data extraction and augmentation are discussed and several examples for use are provided, also demonstrating that some caveats do exist with respect to the source of weather data. Full article
(This article belongs to the Section Spatial Data Science and Digital Earth)
Show Figures

Figure 1

9 pages, 752 KiB  
Data Descriptor
Open Georeferenced Field Data on Forest Types and Species for Biodiversity Assessment and Remote Sensing Applications
by Patrizia Gasparini, Lucio Di Cosmo, Antonio Floris, Federica Murgia and Maria Rizzo
Data 2025, 10(3), 30; https://doi.org/10.3390/data10030030 - 21 Feb 2025
Viewed by 597
Abstract
Forest ecosystems are important for biodiversity conservation, climate regulation and climate change mitigation, soil and water protection, and the recreation and provision of raw materials. This paper presents a dataset on forest type and tree species composition for 934 georeferenced plots located in [...] Read more.
Forest ecosystems are important for biodiversity conservation, climate regulation and climate change mitigation, soil and water protection, and the recreation and provision of raw materials. This paper presents a dataset on forest type and tree species composition for 934 georeferenced plots located in Italy. The forest type is classified in the field consistently with the Italian National Forest Inventory (NFI) based on the dominant tree species or species group. Tree species composition is provided by the percent crown cover of the main five species in the plot. Additional data on conifer and broadleaves pure/mixed condition, total tree and shrub cover, forest structure, sylvicultural system, development stage, and local land position are provided. The surveyed plots are distributed in the central–eastern Alps, in the central Apennines, and in the southern Apennines; they represent a wide range of species composition, ecological conditions, and silvicultural practices. Data were collected as part of a project aimed at developing a classification algorithm based on hyperspectral data. The dataset was made publicly available as it refers to forest types and species widespread in many countries of Central and Southern Europe and is potentially useful to other researchers for the study of forest biodiversity or for remote sensing applications. Full article
Show Figures

Figure 1

19 pages, 251 KiB  
Data Descriptor
HOSPI Application to Portuguese Hospitals’ Websites
by Delfina Soares, Joana Carvalho and Dimitrios Sarantis
Data 2025, 10(3), 29; https://doi.org/10.3390/data10030029 - 21 Feb 2025
Viewed by 434
Abstract
The Health Online Service Provision Index (HOSPI) is an instrument to assess and monitor hospitals’ websites. The index comprises four criteria—Content, Services, Community Interaction and Technology Features—each with a subset of indicators and sub-indicators. HOSPI was applied to the Portuguese hospitals’ websites in [...] Read more.
The Health Online Service Provision Index (HOSPI) is an instrument to assess and monitor hospitals’ websites. The index comprises four criteria—Content, Services, Community Interaction and Technology Features—each with a subset of indicators and sub-indicators. HOSPI was applied to the Portuguese hospitals’ websites in 2023, originating the dataset described in this article. The article also provides a detailed account of the data collection process, which involved direct observation of the websites and specific treatment methods, ensuring the reliability and validity of the dataset. It underscores the relevance of having this data available and how it can improve service provision online in health facilities and support policymaking. Full article
18 pages, 639 KiB  
Article
A Directory of Datasets for Mining Software Repositories
by Themistoklis Diamantopoulos and Andreas L. Symeonidis
Data 2025, 10(3), 28; https://doi.org/10.3390/data10030028 - 20 Feb 2025
Viewed by 916
Abstract
The amount of software engineering data is constantly growing, as more and more developers employ online services to store their code, keep track of bugs, or even discuss issues. The data residing in these services can be mined to address different research challenges; [...] Read more.
The amount of software engineering data is constantly growing, as more and more developers employ online services to store their code, keep track of bugs, or even discuss issues. The data residing in these services can be mined to address different research challenges; therefore, certain initiatives have been established to encourage sharing research datasets collecting them. In this work, we investigate the effect of such an initiative; we create a directory that includes the papers and the corresponding datasets of the data track of the Mining Software Engineering (MSR) conference. Specifically, our directory includes metadata and citation information for the papers of all data tracks, throughout the last twelve years. We also annotate the datasets according to the data source and further assess their compliance to the FAIR principles. Using our directory, researchers can find useful datasets for their research, or even design methodologies for assessing their quality, especially in the software engineering domain. Moreover, the directory can be used for analyzing the citations of data papers, especially with regard to different data categories, as well as for examining their FAIRness score throughout the years, along with its effect on the usage/citation of the datasets. Full article
(This article belongs to the Section Information Systems and Data Management)
Show Figures

Figure 1

29 pages, 4066 KiB  
Article
SAPEx-D: A Comprehensive Dataset for Predictive Analytics in Personalized Education Using Machine Learning
by Muhammad Adnan Aslam, Fiza Murtaza, Muhammad Ehatisham Ul Haq, Amanullah Yasin and Numan Ali
Data 2025, 10(3), 27; https://doi.org/10.3390/data10030027 - 20 Feb 2025
Viewed by 1075
Abstract
Education is crucial for leading a productive life and obtaining necessary resources. Higher education institutions are progressively incorporating artificial intelligence into conventional teaching methods as a result of innovations in technology. As a high academic record raises a university’s ranking and increases student [...] Read more.
Education is crucial for leading a productive life and obtaining necessary resources. Higher education institutions are progressively incorporating artificial intelligence into conventional teaching methods as a result of innovations in technology. As a high academic record raises a university’s ranking and increases student career chances, predicting learning success has been a central focus in education. Both performance analysis and providing high-quality instruction are challenges faced by modern schools. Maintaining high academic standards, juggling life and academics, and adjusting to technology are problems that students must overcome. In this study, we present a comprehensive dataset, SAPEx-D (Student Academic Performance Exploration), designed to predict student performance, encompassing a wide array of personal, familial, academic, and behavioral factors. Our data collection effort at Air University, Islamabad, Pakistan, involved both online and paper questionnaires completed by students across multiple departments, ensuring diverse representation. After meticulous preprocessing to remove duplicates and entries with significant missing values, we retained 494 valid responses. The dataset includes detailed attributes such as demographic information, parental education and occupation, study habits, reading frequencies, and transportation modes. To facilitate robust analysis, we encoded ordinal attributes using label encoding and nominal attributes using one-hot encoding, expanding our dataset from 38 to 88 attributes. Feature scaling was performed to standardize the range and distribution of data, using a normalization technique. Our analysis revealed that factors such as degree major, parental education, reading frequency, and scholarship type significantly influence student performance. The machine learning models applied to this dataset, including Gradient Boosting and Random Forest, demonstrated high accuracy and robustness, underscoring the dataset’s potential for insightful academic performance prediction. In terms of model performance, Gradient Boosting achieved an accuracy of 68.7% and an F1-score of 68% for the eight-class classification task. For the three-class classification, Random Forest outperformed other models, reaching an accuracy of 80.8% and an F1-score of 78%. These findings highlight the importance of comprehensive data in understanding and predicting academic outcomes, paving the way for more personalized and effective educational strategies. Full article
Show Figures

Figure 1

Previous Issue
Next Issue
Back to TopTop