Informatics

18 pages, 3894 KiB

Open AccessArticle

The Development and Evaluation of the Application for Assessing the Fall Risk Factors and the Suggestion to Prevent Falls in Older Adults

by Charupa Lektip, Wiroj Jiamjarasrangsi, Charlee Kaewrat, Jiraphat Nawarat, Chadapa Rungruangbaiyok, Lynette Mackenzie, Voravuth Somsak and Nipaporn Wannaprom

Informatics 2025, 12(2), 53; https://doi.org/10.3390/informatics12020053 - 5 Jun 2025

Viewed by 230

Abstract

Falls are a major health concern for older adults, often leading to injuries and reduced independence. This study develops and evaluates a mobile application integrating two validated fall-risk assessment tools—the Stay Independent Brochure (SIB) and the 44-question Thai Home Falls Hazards Assessment Tool [...] Read more.

Falls are a major health concern for older adults, often leading to injuries and reduced independence. This study develops and evaluates a mobile application integrating two validated fall-risk assessment tools—the Stay Independent Brochure (SIB) and the 44-question Thai Home Falls Hazards Assessment Tool (Thai-HFHAT). The app utilizes a cloud-based architecture with a relational database for real-time analytics and user tracking. In Phase 1, 30 healthcare professionals assessed the app’s technical performance and user experience using a modified System Usability Scale (SUS), achieving a high usability score of 85.2. In Phase 2, 67 older adults used the app for self-assessment, with test–retest reliability evaluated over one week. The app showed strong reliability, with intraclass correlation coefficients (ICCs) of 0.80 for the SIB (Thai-version) and 0.77 for the Thai-HFHAT. Cloud-hosted analytics revealed significant correlations between fall occurrences and both SIB (r = 0.657, p < 0.001) and Thai-HFHAT scores (r = 0.709, p < 0.001), demonstrating the app’s predictive validity. The findings confirm the app’s effectiveness as a self-assessment tool for fall-risk screening among older adults, combining clinical validity with high usability. The integration of culturally adapted tools into a cloud-supported platform demonstrates the value of informatics in geriatric care. Future studies should focus on expanding the app’s reach, incorporating AI-driven risk prediction, enhancing interoperability with electronic health records (EHRs), and improving long-term user engagement to maximize its impact in community settings. Full article

► Show Figures

Graphical abstract

22 pages, 1088 KiB

Open AccessArticle

Intelligent Feature Selection Ensemble Model for Price Prediction in Real Estate Markets

by Daniel Cristóbal Andrade-Girón, William Joel Marin-Rodriguez and Marcelo Gumercindo Zuñiga-Rojas

Informatics 2025, 12(2), 52; https://doi.org/10.3390/informatics12020052 - 20 May 2025

Viewed by 498

Abstract

Real estate is crucial to the global economy, propelling economic and social development. This study examines the effects of dimensionality reduction through Recursive Feature Elimination (RFE), Random Forest (RF), and Boruta on real estate price prediction, assessing ensemble models like Bagging, Random Forest, [...] Read more.

Real estate is crucial to the global economy, propelling economic and social development. This study examines the effects of dimensionality reduction through Recursive Feature Elimination (RFE), Random Forest (RF), and Boruta on real estate price prediction, assessing ensemble models like Bagging, Random Forest, Gradient Boosting, AdaBoost, Stacking, Voting, and Extra Trees. The results indicate that the Stacking model achieved the best performance with an MAE (mean absolute error) of 14,090, MSE (mean squared error) of 5.338 × 10⁸, RMSE (root mean square error) of 23,100, R² of 0.924, and a Concordance Correlation Coefficient (CCC) of 0.960, also demonstrating notable computational efficiency with a time of 67.23 s. Gradient Boosting closely followed, with an MAE of 14,540, R² of 0.920, and a CCC of 0.958, requiring 1.76 s for computation. Variable reduction through RFE in both Gradient Boosting and Stacking led to an increase in MAE by 16.9% and 14.6%, respectively, along with slight reductions in R² and CCC. The application of Boruta reduced the variables to 16, maintaining performance in Stacking, with an increase in MAE of 9.8% and a R² of 0.908. These dimensionality reduction techniques enhanced computational efficiency and proved effective for practical applications without significantly compromising accuracy. Future research should explore automatic hyperparameter optimization and hybrid approaches to improve the adaptability and robustness of models in complex contexts. Full article

(This article belongs to the Section Machine Learning)

► Show Figures

Figure 1

17 pages, 880 KiB

Open AccessArticle

Mitigating Learning Burnout Caused by Generative Artificial Intelligence Misuse in Higher Education: A Case Study in Programming Language Teaching

by Xiaorui Dong, Zhen Wang and Shijing Han

Informatics 2025, 12(2), 51; https://doi.org/10.3390/informatics12020051 - 20 May 2025

Viewed by 474

Abstract

The advent of generative artificial intelligence (GenAI) has significantly transformed the educational landscape. While GenAI offers benefits such as convenient access to learning resources, it also introduces potential risks. This study explores the phenomenon of learning burnout among university students resulting from the [...] Read more.

The advent of generative artificial intelligence (GenAI) has significantly transformed the educational landscape. While GenAI offers benefits such as convenient access to learning resources, it also introduces potential risks. This study explores the phenomenon of learning burnout among university students resulting from the misuse of GenAI in this context. A questionnaire was designed to assess five key dimensions: information overload and cognitive load, overdependence on technology, limitations of personalized learning, shifts in the role of educators, and declining motivation. Data were collected from 143 students across various majors at Shandong Institute of Petroleum and Chemical Technology in China. In response to the issues identified in the survey, the study proposes several teaching strategies, including cheating detection, peer learning and evaluation, and anonymous feedback mechanisms, which were tested through experimental teaching interventions. The results showed positive outcomes, with students who participated in these strategies demonstrating improved academic performance. Additionally, two rounds of surveys indicated that students’ acceptance of additional learning tasks increased over time. This research enhances our understanding of the complex relationship between GenAI and learning burnout, offering valuable insights for educators, policymakers, and researchers on how to effectively integrate GenAI into education while mitigating its negative impacts and fostering healthier learning environments. The dataset, including detailed survey questions and results, is available for download on GitHub. Full article

(This article belongs to the Special Issue Generative AI in Higher Education: Applications, Implications, and Future Directions)

► Show Figures

Figure 1

19 pages, 734 KiB

Open AccessArticle

A Study of Deep Learning Models for Audio Classification of Infant Crying in a Baby Monitoring System

by Denisa Maria Herlea, Bogdan Iancu and Eugen-Richard Ardelean

Informatics 2025, 12(2), 50; https://doi.org/10.3390/informatics12020050 - 16 May 2025

Viewed by 403

Abstract

This study investigates the ability of well-known deep learning models, such as ResNet and EfficientNet, to perform audio-based infant cry detection. By comparing the performance of different machine learning algorithms, this study seeks to determine the most effective approach for the detection of [...] Read more.

This study investigates the ability of well-known deep learning models, such as ResNet and EfficientNet, to perform audio-based infant cry detection. By comparing the performance of different machine learning algorithms, this study seeks to determine the most effective approach for the detection of infant crying, enhancing the functionality of baby monitoring systems and contributing to a more advanced understanding of audio-based deep learning applications. Understanding and accurately detecting a baby’s cries is crucial for ensuring their safety and well-being, a concern shared by new and expecting parents worldwide. Despite advancements in child health, as noted by UNICEF’s 2022 report of the lowest ever recorded child mortality rate, there is still room for technological improvement. This paper presents a comprehensive evaluation of deep learning models for infant cry detection, analyzing the performance of various architectures on spectrogram and MFCC feature representations. A key focus is the comparison between pretrained and non-pretrained models, assessing their ability to generalize across diverse audio environments. Through extensive experimentation, ResNet50 and DenseNet trained on spectrograms emerged as the most effective architectures, significantly outperforming other models in classification accuracy. Additionally, the study investigates the impact of feature extraction techniques, dataset augmentation, and model fine-tuning, providing deeper insights into the role of representation learning in audio classification. The findings contribute to the growing field of audio-based deep learning applications, offering a detailed comparative study of model architectures, feature representations, and training strategies for infant cry detection. Full article

(This article belongs to the Section Machine Learning)

► Show Figures

Figure 1

28 pages, 4160 KiB

Open AccessArticle

Analyzing the Overturn of Roe v. Wade: A Term Co-Occurrence Network Analysis of YouTube Comments

by Rodina Bizri-Baryak, Lana V. Ivanitskaya, Elina V. Erzikova and Gary L. Kreps

Informatics 2025, 12(2), 49; https://doi.org/10.3390/informatics12020049 - 14 May 2025

Viewed by 586

Abstract

Objective: This study examines YouTube comments following the overturn of Roe v. Wade, investigating how perceptions of health implications differ based on commenters’ gender and abortion stance. Methods: Using Netlytic, 25,730 comments were extracted from YouTube videos discussing the overturn of Roe v. [...] Read more.

Objective: This study examines YouTube comments following the overturn of Roe v. Wade, investigating how perceptions of health implications differ based on commenters’ gender and abortion stance. Methods: Using Netlytic, 25,730 comments were extracted from YouTube videos discussing the overturn of Roe v. Wade, half of which featured physicians discussing public health implications. Manual coding of 21% of the comments identified discussions on abortion stance and medical implications, while Gender API approximated the commenters’ gender. A term co-occurrence network was generated with VOSviewer to visualize key terms and their interrelations. Custom overlays explored patterns related to gender, abortion views, and medical implications, and comparisons within these overlays intersected with the medical implications overlay to illustrate contextual differences across demographics. Results: Four clusters emerged in the network: Constitutional Law, addressing the U.S. Constitution’s interpretation and legal impacts; Reproductive Rights and Responsibility, discussing alternatives to abortion and access; Human Development, exploring the intersection of abortion laws and individual beliefs; and Religious Beliefs, linking abortion laws to faith. Prochoice users focused on medical and socioeconomic impacts on women, whereas prolife users emphasized the prevention of unwanted pregnancies and moral considerations. Gender analysis revealed males centered on constitutional issues, while females highlighted medical and personal effects. Conclusion: The findings underscore that monitoring YouTube discourse offers valuable insights into public responses to shifts in health policy. Full article

► Show Figures

Figure 1

26 pages, 9421 KiB

Open AccessArticle

Machine-Learning-Based Classification of Electronic Devices Using an IoT Smart Meter

by Paulo Eugênio da Costa Filho, Leonardo Augusto de Aquino Marques, Israel da S. Felix de Lima, Ewerton Leandro de Sousa, Márcio Eduardo Kreutz, Augusto V. Neto, Eduardo Nogueira Cunha and Dario Vieira

Informatics 2025, 12(2), 48; https://doi.org/10.3390/informatics12020048 - 12 May 2025

Viewed by 531

Abstract

This study investigates the implementation of artificial intelligence (AI) algorithms on resource-constrained edge devices, such as ESP32 and Raspberry Pi, within the context of smart grid (SG) applications. Specifically, it proposes a smart-meter-based system capable of classifying and detecting the Internet of Things [...] Read more.

This study investigates the implementation of artificial intelligence (AI) algorithms on resource-constrained edge devices, such as ESP32 and Raspberry Pi, within the context of smart grid (SG) applications. Specifically, it proposes a smart-meter-based system capable of classifying and detecting the Internet of Things (IoT) electronic devices at the extreme edge. The smart meter developed in this work acquires real-time voltage and current signals from connected devices, which are used to train and deploy lightweight machine learning models—Multi-Layer Perceptron (MLP) and K-Nearest Neighbor (KNN)—directly on edge hardware. The proposed system is integrated into the Artificial Intelligence in the Internet of Things for Smart Grids IAIoSGT architecture, which supports edge–cloud processing and real-time decision-making. A literature review highlights the key gaps in the existing approaches, particularly the lack of embedded intelligence for load identification at the edge. The experimental results emphasize the importance of data preprocessing—especially normalization—in optimizing model performance, revealing distinct behavior between MLP and KNN models depending on the platform. The findings confirm the feasibility of performing accurate low-latency classification directly on smart meters, reinforcing the potential of scalable AI-powered energy monitoring systems in SG. Full article

(This article belongs to the Special Issue The Smart Cities Continuum via Machine Learning and Artificial Intelligence)

► Show Figures

Figure 1

18 pages, 934 KiB

Open AccessSystematic Review

Health-Related Issues of Immersive Technologies: A Systematic Literature Review

by Nkosikhona Theoren Msweli and Mampilo Phahlane

Informatics 2025, 12(2), 47; https://doi.org/10.3390/informatics12020047 - 7 May 2025

Viewed by 762

Abstract

The adoption of immersive technologies, such as virtual reality (VR) and augmented reality (AR), is transforming sectors like healthcare, education, entertainment, and retail by offering innovative, simulated experiences. These technologies provide significant benefits, such as enhanced learning, improved patient outcomes, and innovative rehabilitation [...] Read more.

The adoption of immersive technologies, such as virtual reality (VR) and augmented reality (AR), is transforming sectors like healthcare, education, entertainment, and retail by offering innovative, simulated experiences. These technologies provide significant benefits, such as enhanced learning, improved patient outcomes, and innovative rehabilitation tools. However, their use also raises concerns about user comfort and potential health impacts. This systematic literature review examines the positive and negative health implications of immersive technologies, drawing insights from 104 peer-reviewed articles. The findings highlight therapeutic and rehabilitation benefits, such as treating anxiety and improving motor skills, alongside physical health concerns like eye strain and cybersickness, and mental health challenges, including cognitive overload and addiction. The study identifies key demographics most susceptible to these effects, such as children, the elderly, and individuals with pre-existing health conditions. Recommendations for mitigating risks include ergonomic device design, synchronized sensory inputs, and user training. This research underscores the need for the responsible and ethical development of immersive technologies, ensuring they enhance real-world experiences without compromising user well-being. Future studies should focus on long-term health implications, inclusive design, and establishing guidelines to maximize benefits while minimizing risks. Full article

► Show Figures

Figure 1

27 pages, 411 KiB

Open AccessSystematic Review

Artificial Neural Networks for Image Processing in Precision Agriculture: A Systematic Literature Review on Mango, Apple, Lemon, and Coffee Crops

by Christian Unigarro, Jorge Hernandez and Hector Florez

Informatics 2025, 12(2), 46; https://doi.org/10.3390/informatics12020046 - 6 May 2025

Viewed by 600

Abstract

Precision agriculture is an approach that uses information technologies to improve and optimize agricultural production. It is based on the collection and analysis of agricultural data to support decision making in agricultural processes. In recent years, Artificial Neural Networks (ANNs) have demonstrated significant [...] Read more.

Precision agriculture is an approach that uses information technologies to improve and optimize agricultural production. It is based on the collection and analysis of agricultural data to support decision making in agricultural processes. In recent years, Artificial Neural Networks (ANNs) have demonstrated significant benefits in addressing precision agriculture needs, such as pest detection, disease classification, crop state assessment, and soil quality evaluation. This article aims to perform a systematic literature review on how ANNs with an emphasis on image processing can assess if fruits such as mango, apple, lemon, and coffee are ready for harvest. These specific crops were selected due to their diversity in color and size, providing a representative sample for analyzing the most commonly employed ANN methods in agriculture, especially for fruit ripening, damage, pest detection, and harvest prediction. This review identifies Convolutional Neural Networks (CNNs), including commonly employed architectures such as VGG16 and ResNet50, as highly effective, achieving accuracies ranging between 83% and 99%. Additionally, it discusses the integration of hardware and software, image preprocessing methods, and evaluation metrics commonly employed. The results reveal the notable underuse of vegetation indices and infrared imaging techniques for detailed fruit quality assessment, indicating valuable opportunities for future research. Full article

► Show Figures

Figure 1

30 pages, 1834 KiB

Open AccessReview

State-of-the-Art Cross-Platform Mobile Application Development Frameworks: A Comparative Study of Market and Developer Trends

by Gregor Jošt and Viktor Taneski

Informatics 2025, 12(2), 45; https://doi.org/10.3390/informatics12020045 - 28 Apr 2025

Viewed by 912

Abstract

Cross-platform mobile application development has gained significant traction in recent years, driven by the growing demand for efficient, cost-effective solutions that cater to both iOS and Android platforms. This paper presents a state-of-the-art review of cross-platform mobile application development, emphasizing the industry trends, [...] Read more.

Cross-platform mobile application development has gained significant traction in recent years, driven by the growing demand for efficient, cost-effective solutions that cater to both iOS and Android platforms. This paper presents a state-of-the-art review of cross-platform mobile application development, emphasizing the industry trends, framework popularity, and adoption in the job market. By analyzing developer preferences, community engagement, and market demand, this study provides a comprehensive overview of how cross-platform mobile development frameworks shape the mobile development landscape. The research employs a data-driven methodology, drawing insights from three key categories: Developer Sentiment and Survey Data, Community Engagement and Usage Data, and Market Adoption and Job Market Data. By analyzing these factors, the study identifies the key challenges and emerging trends shaping cross-platform mobile application development. It assesses the most widely used frameworks, comparing their strengths and weaknesses in real-world applications. Furthermore, the research examines the industry adoption patterns and the presence of these frameworks in job market trends. Unlike earlier research, which included now-obsolete platforms like Windows Phone and frameworks such as Xamarin, this study is tailored to the current cross-platform mobile application development market landscape. The conclusions offer actionable insights for developers and researchers, equipping them with the knowledge needed to navigate the evolving cross-platform mobile application development ecosystem effectively. Full article

► Show Figures

Figure 1

24 pages, 1408 KiB

Open AccessArticle

Detecting Student Engagement in an Online Learning Environment Using a Machine Learning Algorithm

by Youssra Bellarhmouch, Hajar Majjate, Adil Jeghal, Hamid Tairi and Nadia Benjelloun

Informatics 2025, 12(2), 44; https://doi.org/10.3390/informatics12020044 - 28 Apr 2025

Viewed by 842

Abstract

This paper examines online learner engagement, a complex concept encompassing several dimensions (behavioral, emotional, and cognitive) and recognized as a key indicator of learning effectiveness. Engagement involves participation, motivation, persistence, and reflection, facilitating content understanding. Predicting engagement, particularly behavioral engagement, encourages interaction and [...] Read more.

This paper examines online learner engagement, a complex concept encompassing several dimensions (behavioral, emotional, and cognitive) and recognized as a key indicator of learning effectiveness. Engagement involves participation, motivation, persistence, and reflection, facilitating content understanding. Predicting engagement, particularly behavioral engagement, encourages interaction and aids teachers in adjusting their methods. The aim is to develop a predictive model to classify learners based on their engagement, using indicators such as academic outcomes to identify signs of difficulty. This study demonstrates that engagement in quizzes and exams predicts engagement in lessons, promoting personalized learning. We utilized supervised machine learning algorithms to forecast engagement at three levels: quizzes, exams, and lessons, drawing from a Kaggle database. Quiz and exam scores were employed to create predictive models for lessons. The performance of the models was evaluated using classic metrics such as precision, recall, and F1-score. The Decision Tree model emerged as the best performer among those evaluated, achieving 97% and 98.49% accuracy in predicting quiz and exam engagement, respectively. The K-Nearest Neighbors (KNN) and Gradient Boosting models also showed commendable performance, albeit slightly less effective than the Decision Tree. The results indicate a strong correlation between engagement predictions across the three levels. This suggests that engagement in quizzes and exams, known as assessments, is a pertinent indicator of overall engagement. Active learners tend to perform better in these assessments. Early identification of at-risk learners allows for targeted interventions, optimizing their engagement. Full article

► Show Figures

Figure 1

12 pages, 998 KiB

Open AccessArticle

Leveraging K-Means Clustering and Z-Score for Anomaly Detection in Bitcoin Transactions

by Jinish Patel, Joseph Reiner, Brenden Stilwell, Abdullah Wahbeh and Raed Seetan

Informatics 2025, 12(2), 43; https://doi.org/10.3390/informatics12020043 - 25 Apr 2025

Viewed by 1249

Abstract

With the growing popularity of cryptocurrencies, detecting potential market manipulation and fraudulent activities has become crucial for maintaining market integrity. In this study, we aim to detect anomalous Bitcoin transactions using an integrated approach by combining clustering techniques with statistical outlier detection. More [...] Read more.

With the growing popularity of cryptocurrencies, detecting potential market manipulation and fraudulent activities has become crucial for maintaining market integrity. In this study, we aim to detect anomalous Bitcoin transactions using an integrated approach by combining clustering techniques with statistical outlier detection. More specifically, anomalies were detected using three approaches: a distance-based method, flagging points with distances greater than the 95th percentile from their cluster centers; a statistical method, identifying transactions with any feature having an absolute Z-score greater than 3; and a hybrid approach, where transactions flagged by either method were considered anomalous. Using sample subset Bitcoin transaction data from 2015, our results showed that the combined approach was able to achieve the best performance with a total of 6492 (6.61%) detected anomalous transactions out of a total of 98,151 transactions. Full article

(This article belongs to the Section Machine Learning)

► Show Figures

Figure 1

10 pages, 644 KiB

Open AccessArticle

Enhanced Preoperative Pancreatoduodenectomy Patient Education Using Mixed Reality Technology: A Randomized Controlled Pilot Study

by Jessica Heard, Paul Murdock, Juan Malo, Joseph Lim, Sourodip Mukharjee and Rohan Jeyarajah

Informatics 2025, 12(2), 42; https://doi.org/10.3390/informatics12020042 - 23 Apr 2025

Viewed by 428

Abstract

(1) Background: Mixed Reality (MR) technology, such as the HoloLens, offers a novel approach to preoperative education. This study evaluates its feasibility and effectiveness in improving patient comprehension and comfort during informed consent for pancreatoduodenectomy. (2) Methods: A single-center, randomized, controlled pilot study [...] Read more.

(1) Background: Mixed Reality (MR) technology, such as the HoloLens, offers a novel approach to preoperative education. This study evaluates its feasibility and effectiveness in improving patient comprehension and comfort during informed consent for pancreatoduodenectomy. (2) Methods: A single-center, randomized, controlled pilot study was conducted between February and May 2023. Patients recommended for pancreatoduodenectomy were randomized into a control group receiving standard education or an intervention group using the HoloLens. Pre- and post-intervention surveys assessed patient understanding and comfort. (3) Results: Nineteen patients participated (8 HoloLens, 11 control). Both groups showed improved comprehension post-intervention, but only the HoloLens group demonstrated a statistically significant increase (Z = −2.524, p = 0.012). MR users had a greater understanding of surgical steps compared to controls, and 75% of participants in both groups reported high comfort levels with the surgery. MR integration was feasible and did not disrupt clinical workflow. (4) Conclusions: These findings suggest that MR can enhance preoperative education for complex procedures. However, limitations include the small sample size and single-center design, necessitating larger studies to confirm its broader applicability. MR-based education represents a promising tool to improve patient engagement and comprehension in surgical decision making. Full article

► Show Figures

Figure 1

22 pages, 2500 KiB

Open AccessArticle

Are We Inclusive? Accessibility Challenges in Philippine E-Government Websites

by Paul Bokingkito, Jr., Jerame Beloy, Jerina Jean Ecleo, Apple Rose Alce, Nenen Borinaga and Adrian Galido

Informatics 2025, 12(2), 41; https://doi.org/10.3390/informatics12020041 - 15 Apr 2025

Viewed by 1198

Abstract

Web accessibility is essential for e-government in the Philippines to ensure that all citizens, including those with disabilities, can access important information and services. This study evaluates government web accessibility using the Web Content Accessibility Guidelines 2.0 from the World Wide Web Consortium [...] Read more.

Web accessibility is essential for e-government in the Philippines to ensure that all citizens, including those with disabilities, can access important information and services. This study evaluates government web accessibility using the Web Content Accessibility Guidelines 2.0 from the World Wide Web Consortium and web presence based on the Government Website Template Design guidelines. A combination of automated testing tools and visual inspections was used for the assessment. Results showed significant discrepancies between web presence and web accessibility. Web presence compliance ranged from 28% to 82.67%, averaging 53.43%. Web accessibility scored higher, with compliance rates ranging from 62.32% to 97.1% and an average of 82.5%. This indicates that while many government agencies have focused on accessibility, there is a need to improve their digital services and visibility. A well-structured and user-friendly website is vital. However, without expanded online services, mobile accessibility, and transactional features, the full potential of digital governance remains untapped. Future studies are directed to aid government agencies with adopting accessible design principles, conducting regular audits, collaborating with disability advocacy groups, and integrating assistive technologies to foster a more inclusive and efficient digital government ecosystem. Full article

► Show Figures

Figure 1

14 pages, 268 KiB

Open AccessArticle

Machine Learning Applied to Improve Prevention of, Response to, and Understanding of Violence Against Women

by Mariana Carolyn Cruz-Mendoza, Roberto Angel Melendez-Armenta, Juana Canul-Reich and Julio Muñoz-Benítez

Informatics 2025, 12(2), 40; https://doi.org/10.3390/informatics12020040 - 11 Apr 2025

Viewed by 649

Abstract

Intimate partner violence (IPV) remains a critical issue that requires data-driven solutions to improve victim profiling and intervention strategies. This study introduces Mujer Segura, an innovative web application designed to collect structured data on IPV cases and predict their severity using machine learning [...] Read more.

Intimate partner violence (IPV) remains a critical issue that requires data-driven solutions to improve victim profiling and intervention strategies. This study introduces Mujer Segura, an innovative web application designed to collect structured data on IPV cases and predict their severity using machine learning models. The methodology integrates Random Forest (RF) and Gradient Boosting Classifier (GBC) algorithms to classify IPV cases by leveraging historical data for predictive analysis. The RF model achieved an accuracy of 97%, with a precision of 1.00 for non-severe cases and 0.96 for severe cases, recall values of 0.93 and 1.00 respectively, and an ROC AUC of 0.9534. The GBC model demonstrated an accuracy of 89%, with a precision of 1.00 for non-severe cases and 0.98 for severe cases, recall values of 0.95 and 1.00 respectively, and an ROC AUC of 0.9891. The application also integrates geospatial visualization tools to identify high-risk areas in the State of Mexico, enabling real-time interventions. These findings confirm that machine learning can enhance the timely detection of IPV cases and support evidence-based decision-making for public safety agencies. Full article

► Show Figures

Figure 1

24 pages, 734 KiB

Open AccessArticle

Transparency Unleashed: Privacy Risks in the Age of E-Government

by Cristian Paguay-Chimarro, David Cevallos-Salas, Ana Rodríguez-Hoyos and José Estrada-Jiménez

Informatics 2025, 12(2), 39; https://doi.org/10.3390/informatics12020039 - 11 Apr 2025

Viewed by 661

Abstract

E-government and transparency are significantly improving public service management by encouraging trust, accountability, and the massive participation of citizens. On the one hand, e-government has facilitated online services to address bureaucratic processes more efficiently. On the other hand, transparency has promoted open access [...] Read more.

E-government and transparency are significantly improving public service management by encouraging trust, accountability, and the massive participation of citizens. On the one hand, e-government has facilitated online services to address bureaucratic processes more efficiently. On the other hand, transparency has promoted open access to public information from the State so that citizens can understand and track aspects of government processes more effectively. However, as both require extensive citizen information management, these initiatives may significantly compromise privacy by exposing personal data. To assess these privacy risks in a concrete scenario, we analyzed 21 public institutions in Ecuador through a proposed taxonomy of 6 categories and 17 subcategories of disclosed personal data on their online portals and websites due to LOTAIP transparency initiative. Moreover, 64 open-access systems from these 21 public institutions that accomplish e-government principles were analyzed through a proposed taxonomy of 8 categories and 77 subcategories of disclosed personal data. Our results suggest that personal data are not handled through suitable protection mechanisms, making them extremely vulnerable to manual and automated exfiltration attacks. The lack of awareness campaigns in Ecuador has also led many citizens to handle their personal data carelessly without being aware of the associated risks. Moreover, Ecuadorian citizens’ privacy is significantly compromised, including personal data from children and teenagers being intentionally exposed through e-government and transparency initiatives. Full article

(This article belongs to the Section Social Informatics and Digital Humanities)

► Show Figures

Graphical abstract

18 pages, 5048 KiB

Open AccessReview

Clustering with Uncertainty: A Literature Review to Address a Cross-Domain Perspective

by Salvatore Flavio Pileggi

Informatics 2025, 12(2), 38; https://doi.org/10.3390/informatics12020038 - 9 Apr 2025

Viewed by 575

Abstract

Clustering is a very popular computational technique that, because of imperfect data, is often applied in the presence of some kind of uncertainty. Taking into account such an uncertainty (and model), the computational output accordingly contributes to increasing the accuracy of the computations [...] Read more.

Clustering is a very popular computational technique that, because of imperfect data, is often applied in the presence of some kind of uncertainty. Taking into account such an uncertainty (and model), the computational output accordingly contributes to increasing the accuracy of the computations and their effectiveness in context. However, there are challenges. This paper presents a literature review on the topic. It aims to identify and discuss the associated body of knowledge according to a cross-domain perspective. A semi-systematic methodology has allowed for the selection of 68 papers, prioritizing the most recent contributions and an intrinsic application-oriented approach. The analysis has underscored the relevance of the topic in the last two decades, in which computation has become somewhat pervasive in the context of inherent data complexity. Furthermore, it has identified a trend of domain-specific solutions over generic-purpose approaches. On one side, this trend enables a more specific set of solutions within specific communities; on the other side, the resulting distributed approach is not always well integrated with the mainstream. The latter aspect may generate a further fragmentation of the body of knowledge, mostly because of some lack of abstraction in the definition of specific problems. While in general terms these gaps are largely understandable within the research community, a lack of implementations to provide ready-to-use resources is critical overall. In more technical terms, solutions in the literature present a certain inclination to mixed methods, in addition to the classic application of Fuzzy Logic and other probabilistic approaches. Last but not least, the propagation of the uncertainty in the current technological context, characterised by data and computational intensive solutions, is not fully analysed and critically discussed in the literature. The conducted analysis intrinsically suggests consolidation and enhanced operationalization though Open Software, which is crucial to establish scientifically sound computational frameworks. Full article

► Show Figures

Figure 1

17 pages, 5441 KiB

Open AccessArticle

Enhancing Cultural Heritage Accessibility Through Three-Dimensional Artifact Visualization on Web-Based Open Frameworks

by Sasithorn Rattanarungrot, Martin White and Supaporn Chairungsee

Informatics 2025, 12(2), 37; https://doi.org/10.3390/informatics12020037 - 9 Apr 2025

Viewed by 692

Abstract

This paper presents an innovative approach to cultural heritage preservation through the development of an open framework that leverages RESTful APIs to make high-fidelity 3D models of cultural artifacts accessible to any application. Focusing on antique kitchenware utensils from the Nakhon Si Thammarat [...] Read more.

This paper presents an innovative approach to cultural heritage preservation through the development of an open framework that leverages RESTful APIs to make high-fidelity 3D models of cultural artifacts accessible to any application. Focusing on antique kitchenware utensils from the Nakhon Si Thammarat National Museum in Thailand, this research utilizes photogrammetry to create detailed 3D models, which are then made available on a web-based platform, accessible globally via standardized HTTP requests. The framework enables real-time access to 3D cultural content, overcoming the geographical and physical barriers that often limit access to cultural heritage. By integrating these 3D models into RESTful APIs, the project not only preserves delicate artifacts but also enhances their educational and cultural value through interactive accessibility. This system demonstrates the practical application of digital preservation technologies and sets a precedent for future initiatives aiming to digitize and disseminate cultural artifacts more broadly. The implications of this study extend beyond preservation to include enhanced global accessibility, enriched educational resources, and a more inclusive approach to cultural engagement. This project illustrates the transformative potential of digital technologies in preserving, accessing, and experiencing cultural heritage worldwide. Full article

(This article belongs to the Section Human-Computer Interaction)

► Show Figures

Figure 1

22 pages, 297 KiB

Open AccessArticle

Exploring the Ethical Implications of Using Generative AI Tools in Higher Education

by Elena Đerić, Domagoj Frank and Dijana Vuković

Informatics 2025, 12(2), 36; https://doi.org/10.3390/informatics12020036 - 7 Apr 2025

Viewed by 1931

Abstract

A significant portion of the academic community, including students, teachers, and researchers, has incorporated generative artificial intelligence (GenAI) tools into their everyday tasks. Alongside increased productivity and numerous benefits, specific challenges that are fundamental to maintaining academic integrity and excellence must be addressed. [...] Read more.

A significant portion of the academic community, including students, teachers, and researchers, has incorporated generative artificial intelligence (GenAI) tools into their everyday tasks. Alongside increased productivity and numerous benefits, specific challenges that are fundamental to maintaining academic integrity and excellence must be addressed. This paper examines whether ethical implications related to copyrights and authorship, transparency, responsibility, and academic integrity influence the usage of GenAI tools in higher education, with emphasis on differences across academic segments. The findings, based on a survey of 883 students, teachers, and researchers at University North in Croatia, reveal significant differences in ethical awareness across academic roles, gender, and experience with GenAI tools. Teachers and researchers demonstrated the highest awareness of ethical principles, personal responsibility, and potential negative consequences, while students—particularly undergraduates—showed lower levels, likely due to limited exposure to structured ethical training. Gender differences were also significant, with females consistently demonstrating higher awareness across all ethical dimensions compared to males. Longer experience with GenAI tools was associated with greater ethical awareness, emphasizing the role of familiarity in fostering understanding. Although strong correlations were observed between ethical dimensions, their connection to future adoption was weaker, highlighting the need to integrate ethical education with practical strategies for responsible GenAI tool use. Full article

17 pages, 5507 KiB

Open AccessArticle

Markov-CVAELabeller: A Deep Learning Approach for the Labelling of Fault Data

by Christian Velasco-Gallego and Nieves Cubo-Mateo

Informatics 2025, 12(2), 35; https://doi.org/10.3390/informatics12020035 - 25 Mar 2025

Viewed by 612

Abstract

The lack of fault data is still a major concern in the area of smart maintenance, as these data are required to perform an adequate diagnostics and prognostics of the system. In some instances, fault data are adequately collected, even though the fault [...] Read more.

The lack of fault data is still a major concern in the area of smart maintenance, as these data are required to perform an adequate diagnostics and prognostics of the system. In some instances, fault data are adequately collected, even though the fault labels are missing. Accordingly, the development of methodologies that generate these missing fault labels is required. In this study, Markov-CVAELabeller is introduced in an attempt to address the lack of fault label challenge. Markov-CVAELabeller comprises three main phases: (1) image encoding through the application of the first-order Markov chain, (2) latent space representation through the consideration of a convolutional variational autoencoder (CVAE), and (3) clustering analysis through the implementation of k-means. Additionally, to evaluate the accuracy of the method, a convolutional neural network (CNN) is considered as part of the fault classification task. A case study is also presented to highlight the performance of the method. Specifically, a hydraulic test rig is considered to assess its condition as part of the fault diagnosis framework. Results indicate the promising applications that this type of methods can facilitate, as the average accuracy presented in this study was 97%. Full article

► Show Figures

Figure 1

17 pages, 5550 KiB

Open AccessArticle

Offline System for 2D Indoor Navigation Utilizing Advanced Data Structures

by Jorge Luis Veloz, Leo Sebastián Intriago, Jean Carlos Palma, Andrea Katherine Alcívar-Cedeño, Álvaro Antón-Sacho, Pablo Fernández-Arias, Edwan Anderson Ariza and Diego Vergara

Informatics 2025, 12(2), 34; https://doi.org/10.3390/informatics12020034 - 21 Mar 2025

Viewed by 703

Abstract

This study introduces a robust offline system for 2D indoor navigation, developed to address common challenges such as complex layouts and connectivity constraints in diverse environments. The system leverages advanced spatial modeling techniques to optimize pathfinding and resource efficiency. Utilizing a structured development [...] Read more.

This study introduces a robust offline system for 2D indoor navigation, developed to address common challenges such as complex layouts and connectivity constraints in diverse environments. The system leverages advanced spatial modeling techniques to optimize pathfinding and resource efficiency. Utilizing a structured development process, the proposed solution integrates lightweight data structures and modular components to minimize computational load and enhance scalability. Experimental validation involved a comparative approach: traditional navigation methods were assessed against the proposed system, focusing on usability, search efficiency, and user satisfaction. The results demonstrate that the offline system significantly improves navigation performance and user experience, particularly in environments with limited connectivity. By providing intuitive navigation tools and seamless offline operation, the system enhances accessibility for users in educational and other complex settings. Future work aims to extend this approach to incorporate additional features, such as dynamic adaptability and expanded application in sectors like healthcare and public services. Full article

(This article belongs to the Section Human-Computer Interaction)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Informatics, Volume 12, Issue 2 (June 2025) – 20 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI