Saved Queries

This study introduces an enhanced Intrusion Detection System (IDS) framework for Denial-of-Service (DoS) attacks, utilizing network traffic inter-arrival time (IAT) analysis. By examining the timing between packets and other statistical features, we detected patterns of malicious activity, allowing early and effective DoS threat mitigation. We generate real DoS traffic, including normal, Internet Control Message Protocol (ICMP), Smurf attack, and Transmission Control Protocol (TCP) classes, and develop nine predictive algorithms, combining traditional machine learning and advanced deep learning techniques with optimization methods, including the synthetic minority sampling technique (SMOTE) and grid search (GS). Our findings reveal that while traditional machine learning achieved moderate accuracy, it struggled with imbalanced datasets. In contrast, Deep Neural Network (DNN) models showed significant improvements with optimization, with DNN combined with GS (DNN-GS) reaching 89% accuracy. However, we also used Recurrent Neural Networks (RNNs) combined with SMOTE and GS (RNN-SMOTE-GS), which emerged as the best-performing with a precision of 97%, demonstrating the effectiveness of combining SMOTE and GS and highlighting the critical role of advanced optimization techniques in enhancing the detection capabilities of IDS models for the accurate classification of various types of network traffic and attacks. Full article

►▼ Show Figures

Figure 1

17 pages, 497 KiB

Open AccessArticle

Generative Data Modelling for Diverse Populations in Africa: Insights from South Africa

by Sally Sonia Simmons, John Elvis Hagan and Thomas Schack

Information 2025, 16(7), 612; https://doi.org/10.3390/info16070612 (registering DOI) - 17 Jul 2025

Abstract

Studies on the demography and health of racially diverse African populations are scarce, particularly due to lingering data challenges. Generative data modelling has emerged as a valuable solution to this burden. The study, therefore, examined the efficacy of Conditional Tabular GAN (CTGAN), CopulaGAN, and Tabula Variational Autoencoder (TVAE) for generating synthetic but realistic demographic and health data. This study employed the World Health Organisation stigy on global ageing and adult health survey (SAGE) Wave 1 South African data (n = 4227). Information missing from SAGE Wave 1, including demographic (e.g., race, age) and health (e.g., hypertension, blood pressure) indicators, were imputed using Generative Adversarial Imputation Nets (GAIN). CopulaGAN, CTGAN, and TVAE, sourced from the sdv 1.24.1 python library, generated 104,227 synthetic records based on the SAGE data constituents. The outcomes were accessed with similarity and machine learning (XGBoost) augmentation metrics (sourced from the sdmetrics 0.21.0 python library), including column shapes and overall and precision ratio scores. Generally, the GAIN imputations resulted in data with properties that were comparable to original and with no missing information. CTGAN’s (89.20%) overall quality of performance was above that of TVAE (86.50%) and CopulaGAN (88.45%). These findings underscore the usefulness of generative data modelling in addressing data quality challenges in diverse populations to enhance actionable health research and policy implementation. Full article

►▼ Show Figures

Graphical abstract

20 pages, 267 KiB

Open AccessArticle

A Systems Thinking Approach to Political Polarization and Encounters of Dysrecognition

by Gregory A. Thompson and Soren Pearce

Humans 2025, 5(3), 17; https://doi.org/10.3390/humans5030017 (registering DOI) - 17 Jul 2025

Abstract

In this article, we employ a Batesonian systems thinking approach to analyze politically polarized and politically polarizing encounters in the contemporary United States. We bring together Bateson’s concepts of schismogenesis, double binds, metacommunication, and transcontextualism with recent work on recognition and resonance in order to show how these encounters create moments of transcontextual double binds that produce mutual dysrecognition. We show how these moments of mutual dysrecognition become both animating forces of political polarization in the moment while also becoming constitutive poetic resonances for making sense of future events. When these moments of dysrecognition are considered alongside the removal of mechanisms that restrain schismogenesis, the United States body politic is becoming increasingly schizophrenic—split in two with both parts incommunicado with the other such that the whole system is veering towards collapse. We close by briefly considering the kind of deutero-learning, to use Bateson’s term, that might help to stave off such a collapse. Full article

(This article belongs to the Special Issue Systems Thinking in Anthropology: Understanding Cultural Complexity in the Era of Super-diversity)

14 pages, 555 KiB

Open AccessArticle

A Novel Hyper-Heuristic Algorithm for Bayesian Network Structure Learning Based on Feature Selection

by Yinglong Dang, Xiaoguang Gao and Zidong Wang

Axioms 2025, 14(7), 538; https://doi.org/10.3390/axioms14070538 (registering DOI) - 17 Jul 2025

Abstract

Bayesian networks (BNs) are effective and universal tools for addressing uncertain knowledge. BN learning includes structure learning and parameter learning, and structure learning is its core. The topology of a BN can be determined by expert domain knowledge or obtained through data analysis. However, when many variables exist in a BN, relying only on expert knowledge is difficult and infeasible. Therefore, the current research focus is to build a BN via data analysis. However, current data learning methods have certain limitations. In this work, we consider a combination of expert knowledge and data learning methods. In our algorithm, the hard constraints are derived from highly reliable expert knowledge, and some conditional independent information is mined by feature selection as a soft constraint. These structural constraints are reasonably integrated into an exponential Monte Carlo with counter (EMCQ) hyper-heuristic algorithm. A comprehensive experimental study demonstrates that our proposed method exhibits more robustness and accuracy compared to alternative algorithms. Full article

(This article belongs to the Special Issue Advances in Mathematical Optimization Algorithms and Its Applications)

►▼ Show Figures

Figure 1

22 pages, 761 KiB

Open AccessReview

Insights from Mass Spectrometry-Based Proteomics on Cryptococcus neoformans

by Jovany Jordan Betancourt and Kirsten Nielsen

J. Fungi 2025, 11(7), 529; https://doi.org/10.3390/jof11070529 (registering DOI) - 17 Jul 2025

Abstract

Cryptococcus neoformans is an opportunistic fungal pathogen and causative agent of cryptococcosis and cryptococcal meningitis (CM). Cryptococcal disease accounts for up to 19% of AIDS-related mortalities globally, warranting its label as a pathogen of critical priority by the World Health Organization. Standard treatments for CM rely heavily on high doses of antifungal agents for long periods of time, contributing to the growing issue of antifungal resistance. Moreover, mortality rates for CM are still incredibly high (13–78%). Attempts to create new and effective treatments have been slow due to the complex and diverse set of immune-evasive and survival-enhancing virulence factors that C. neoformans employs. To bolster the development of better clinical tools, deeper study into host–Cryptococcus proteomes is needed to identify clinically relevant proteins, pathways, antigens, and beneficial host response mechanisms. Mass spectrometry-based proteomics approaches serve as invaluable tools for investigating these complex questions. Here, we discuss some of the insights into cryptococcal disease and biology learned using proteomics, including target proteins and pathways regulating Cryptococcus virulence factors, metabolism, and host defense responses. By utilizing proteomics to probe deeper into these protein interaction networks, new clinical tools for detecting, diagnosing, and treating C. neoformans can be developed. Full article

(This article belongs to the Special Issue Proteomic Studies of Pathogenic Fungi and Hosts)

►▼ Show Figures

Figure 1

26 pages, 2018 KiB

Open AccessReview

Influence of Light Regimes on Production of Beneficial Pigments and Nutrients by Microalgae for Functional Plant-Based Foods

by Xiang Huang, Feng Wang, Obaid Ur Rehman, Xinjuan Hu, Feifei Zhu, Renxia Wang, Ling Xu, Yi Cui and Shuhao Huo

Foods 2025, 14(14), 2500; https://doi.org/10.3390/foods14142500 (registering DOI) - 17 Jul 2025

Abstract

Microalgal biomass has emerged as a valuable and nutrient-rich source of novel plant-based foods of the future, with several demonstrated benefits. In addition to their green and health-promoting characteristics, these foods exhibit bioactive properties that contribute to a range of physiological benefits. Photoautotrophic microalgae are particularly important as a source of food products due to their ability to biosynthesize high-value compounds. Their photosynthetic efficiency and biosynthetic activity are directly influenced by light conditions. The primary goal of this study is to track the changes in the light requirements of various high-value microalgae species and use advanced systems to regulate these conditions. Artificial intelligence (AI) and machine learning (ML) models have emerged as pivotal tools for intelligent microalgal cultivation. This approach involves the continuous monitoring of microalgal growth, along with the real-time optimization of environmental factors and light conditions. By accumulating data through cultivation experiments and training AI models, the development of intelligent microalgae cell factories is becoming increasingly feasible. This review provides a concise overview of the regulatory mechanisms that govern microalgae growth in response to light conditions, explores the utilization of microalgae-based products in plant-based foods, and highlights the potential for future research on intelligent microalgae cultivation systems. Full article

(This article belongs to the Special Issue The Role of Microalgae or Cyanobacteria in Major Food Crops and Sustainable Food Production)

►▼ Show Figures

Figure 1

18 pages, 871 KiB

Open AccessReview

Artificial Intelligence-Assisted Selection Strategies in Sheep: Linking Reproductive Traits with Behavioral Indicators

by Ebru Emsen, Muzeyyen Kutluca Korkmaz and Bahadir Baran Odevci

Animals 2025, 15(14), 2110; https://doi.org/10.3390/ani15142110 (registering DOI) - 17 Jul 2025

Abstract

Reproductive efficiency is a critical determinant of productivity and profitability in sheep farming. Traditional selection methods have largely relied on phenotypic traits and historical reproductive records, which are often limited by subjectivity and delayed feedback. Recent advancements in artificial intelligence (AI), including video tracking, wearable sensors, and machine learning (ML) algorithms, offer new opportunities to identify behavior-based indicators linked to key reproductive traits such as estrus, lambing, and maternal behavior. This review synthesizes the current research on AI-powered behavioral monitoring tools and proposes a conceptual model, ReproBehaviorNet, that maps age- and sex-specific behaviors to biological processes and AI applications, supporting real-time decision-making in both intensive and semi-intensive systems. The integration of accelerometers, GPS systems, and computer vision models enables continuous, non-invasive monitoring, leading to earlier detection of reproductive events and greater breeding precision. However, the implementation of such technologies also presents challenges, including the need for high-quality data, a costly infrastructure, and technical expertise that may limit access for small-scale producers. Despite these barriers, AI-assisted behavioral phenotyping has the potential to improve genetic progress, animal welfare, and sustainability. Interdisciplinary collaboration and responsible innovation are essential to ensure the equitable and effective adoption of these technologies in diverse farming contexts. Full article

(This article belongs to the Special Issue Technological and Statistical Advances in Breeding and Genetics of Sheep and Goat)

►▼ Show Figures

Figure 1

24 pages, 1991 KiB

Open AccessArticle

A Multi-Feature Semantic Fusion Machine Learning Architecture for Detecting Encrypted Malicious Traffic

by Shiyu Tang, Fei Du, Zulong Diao and Wenjun Fan

J. Cybersecur. Priv. 2025, 5(3), 47; https://doi.org/10.3390/jcp5030047 (registering DOI) - 17 Jul 2025

Abstract

With the increasing sophistication of network attacks, machine learning (ML)-based methods have showcased promising performance in attack detection. However, ML-based methods often suffer from high false rates when tackling encrypted malicious traffic. To break through these bottlenecks, we propose EFTransformer, an encrypted flow transformer framework which inherits semantic perception and multi-scale feature fusion, can robustly and efficiently detect encrypted malicious traffic, and make up for the shortcomings of ML in the context of modeling ability and feature adequacy. EFTransformer introduces a channel-level extraction mechanism based on quintuples and a noise-aware clustering strategy to enhance the recognition ability of traffic patterns; adopts a dual-channel embedding method, using Word2Vec and FastText to capture global semantics and subword-level changes; and uses a Transformer-based classifier and attention pooling module to achieve dynamic feature-weighted fusion, thereby improving the robustness and accuracy of malicious traffic detection. Our systematic experiments on the ISCX2012 dataset demonstrate that EFTransformer achieves the best detection performance, with an accuracy of up to 95.26%, a false positive rate (FPR) of 6.19%, and a false negative rate (FNR) of only 5.85%. These results show that EFTransformer achieves high detection performance against encrypted malicious traffic. Full article

(This article belongs to the Section Security Engineering & Applications)

►▼ Show Figures

Figure 1

17 pages, 10396 KiB

Open AccessArticle

Feature Selection Based on Three-Dimensional Correlation Graphs

by Adam Dudáš and Aneta Szoliková

AppliedMath 2025, 5(3), 91; https://doi.org/10.3390/appliedmath5030091 (registering DOI) - 17 Jul 2025

Abstract

The process of feature selection is a critical component of any decision-making system incorporating machine or deep learning models applied to multidimensional data. Feature selection on input data can be performed using a variety of techniques, such as correlation-based methods, wrapper-based methods, or embedded methods. However, many conventionally used approaches do not support backwards interpretability of the selected features, making their application in real-world scenarios impractical and difficult to implement. This work addresses that limitation by proposing a novel correlation-based strategy for feature selection in regression tasks, based on a three-dimensional visualization of correlation analysis results—referred to as three-dimensional correlation graphs. The main objective of this study is the design, implementation, and experimental evaluation of this graphical model through a case study using a multidimensional dataset with 28 attributes. The experiments assess the clarity of the visualizations and their impact on regression model performance, demonstrating that the approach reduces dimensionality while maintaining or improving predictive accuracy, enhances interpretability by uncovering hidden relationships, and achieves better or comparable results to conventional feature selection methods. Full article

►▼ Show Figures

Figure 1

488 KiB

Open AccessProceeding Paper

Digital Twins for Circular Economy Optimization: A Framework for Sustainable Engineering Systems

by Shubham Gupta

Proceedings 2025, 121(1), 4; https://doi.org/10.3390/proceedings2025121004 (registering DOI) - 16 Jul 2025

Abstract

This paper introduces sustainable engineering systems built using digital twin technology and circular economy principles. This research presents a framework for monitoring, modeling, and making decisions in real timusing virtual replicas of physical products, processes, and systems in product lifecycles. A digital twin was used to show that through a digital twin, waste was reduced by 27%, energy consumption was reduced by 32%, and the resource recovery rate increased to 45%. The proposed approach under the framework employs various machine learning algorithms, IoT sensor networks, and advanced data analytics to support closed-loop flows of materials. The results show how digital twins can enhance progress toward the goals the circular economy sets to identify inefficiencies, predict maintenance needs, and optimize the use of resources. This integration is a promising industry approach that will introduce more sustainable operations and maintain economic viability. Full article

►▼ Show Figures

Figure 1

18 pages, 1508 KiB

Open AccessArticle

Development of Co-Amorphous Systems for Inhalation Therapy—Part 1: from Model Prediction to Clinical Success

by Eleonore Fröhlich, Aurora Bordoni, Nila Mohsenzada, Stefan Mitsche, Hartmuth Schröttner and Sarah Zellnitz-Neugebauer

Pharmaceutics 2025, 17(7), 922; https://doi.org/10.3390/pharmaceutics17070922 (registering DOI) - 16 Jul 2025

Abstract

Background/Objectives: The integration of machine learning (ML) and artificial intelligence (AI) has revolutionized the pharmaceutical industry by improving drug discovery, development and manufacturing processes. Based on literature data, an ML model was developed by our group to predict the formation of binary co-amorphous systems (COAMSs) for inhalation therapy. The model’s ability to develop a dry powder formulation with the necessary properties for a predicted co-amorphous combination was evaluated. Methods: An extended experimental validation of the ML model by co-milling and X-ray diffraction analysis for 18 API-API (active pharmaceutical ingredient) combinations is presented. Additionally, one COAMS of rifampicin (RIF) and ethambutol (ETH),two first-line tuberculosis (TB) drugs are developed further for inhalation therapy. Results: The ML model has shown an accuracy of 79% in predicting suitable combinations for 35 APIs used in inhalation therapy; experimental accuracy was demonstrated to be 72%. The study confirmed the successful development of stable COAMSs of RIF-ETH either via spray-drying or co-milling. In particular, the milled COAMSs showed better aerosolization properties (higher ED and FPF with lower standard deviation). Further, RIF-ETH COAMSs show much more reproducible results in terms of drug quantity dissolved over time. Conclusions: ML has been shown to be a suitable tool to predict COAMSs that can be developed for TB treatment by inhalation to save time and cost during the experimental screening phase. Full article

(This article belongs to the Special Issue New Platform for Tuberculosis Treatment)

24 pages, 2667 KiB

Open AccessArticle

Transformer-Driven Fault Detection in Self-Healing Networks: A Novel Attention-Based Framework for Adaptive Network Recovery

by Parul Dubey, Pushkar Dubey and Pitshou N. Bokoro

Mach. Learn. Knowl. Extr. 2025, 7(3), 67; https://doi.org/10.3390/make7030067 - 16 Jul 2025

Abstract

Fault detection and remaining useful life (RUL) prediction are critical tasks in self-healing network (SHN) environments and industrial cyber–physical systems. These domains demand intelligent systems capable of handling dynamic, high-dimensional sensor data. However, existing optimization-based approaches often struggle with imbalanced datasets, noisy signals, and delayed convergence, limiting their effectiveness in real-time applications. This study utilizes two benchmark datasets—EFCD and SFDD—which represent electrical and sensor fault scenarios, respectively. These datasets pose challenges due to class imbalance and complex temporal dependencies. To address this, we propose a novel hybrid framework combining Attention-Augmented Convolutional Neural Networks (AACNN) with transformer encoders, enhanced through Enhanced Ensemble-SMOTE for balancing the minority class. The model captures spatial features and long-range temporal patterns and learns effectively from imbalanced data streams. The novelty lies in the integration of attention mechanisms and adaptive oversampling in a unified fault-prediction architecture. Model evaluation is based on multiple performance metrics, including accuracy, F1-score, MCC, RMSE, and score*. The results show that the proposed model outperforms state-of-the-art approaches, achieving up to 97.14% accuracy and a score* of 0.419, with faster convergence and improved generalization across both datasets. Full article

►▼ Show Figures

Figure 1

35 pages, 1123 KiB

Open AccessArticle

AI-Based Bankruptcy Prediction for Agricultural Firms in Central and Eastern Europe

by Dominika Gajdosikova, Jakub Michulek and Irina Tulyakova

Int. J. Financial Stud. 2025, 13(3), 133; https://doi.org/10.3390/ijfs13030133 - 16 Jul 2025

Abstract

The agriculture sector is increasingly challenged to maintain productivity and sustainability amidst environmental, marketplace, and geopolitical pressures. While precision agriculture enhances physical production, the financial resilience of agricultural firms has been understudied. In this study, machine learning (ML) methods, including logistic regression (LR), decision trees (DTs), and artificial neural networks (ANNs), are employed to predict the bankruptcy risk for Central and Eastern European (CEE) farming firms. All models consistently showed high performance, with AUC values exceeding 0.95. DTs had the highest overall accuracy (95.72%) and F1 score (0.9768), LR had the highest recall (0.9923), and ANNs had the highest discrimination power (AUC = 0.960). Visegrad, Balkan, Baltic, and Eastern Europe subregional models featured economic and structural heterogeneity, reflecting the need for local financial risk surveillance. The results support the development of AI-based early warning systems for agricultural finance, enabling smarter decision-making, regional adaptation, and enhanced sustainability in the sector. Full article

(This article belongs to the Special Issue Advancing Financial Stability and Performance Through AI and Digital Transformation)

►▼ Show Figures

Figure 1

49 pages, 3444 KiB

Open AccessArticle

A Design-Based Research Approach to Streamline the Integration of High-Tech Assistive Technologies in Speech and Language Therapy

by Anna Lekova, Paulina Tsvetkova, Anna Andreeva, Georgi Dimitrov, Tanio Tanev, Miglena Simonska, Tsvetelin Stefanov, Vaska Stancheva-Popkostadinova, Gergana Padareva, Katia Rasheva, Adelina Kremenska and Detelina Vitanova

Technologies 2025, 13(7), 306; https://doi.org/10.3390/technologies13070306 - 16 Jul 2025

Abstract

Currently, high-tech assistive technologies (ATs), particularly Socially Assistive Robots (SARs), virtual reality (VR) and conversational AI (ConvAI), are considered very useful in supporting professionals in Speech and Language Therapy (SLT) for children with communication disorders. However, despite a positive public perception, therapists face difficulties when integrating these technologies into practice due to technical challenges and a lack of user-friendly interfaces. To address this gap, a design-based research approach has been employed to streamline the integration of SARs, VR and ConvAI in SLT, and a new software platform called “ATLog” has been developed for designing interactive and playful learning scenarios with ATs. ATLog’s main features include visual-based programming with graphical interface, enabling therapists to intuitively create personalized interactive scenarios without advanced programming skills. The platform follows a subprocess-oriented design, breaking down SAR skills and VR scenarios into microskills represented by pre-programmed graphical blocks, tailored to specific treatment domains, therapy goals, and language skill levels. The ATLog platform was evaluated by 27 SLT experts using the Technology Acceptance Model (TAM) and System Usability Scale (SUS) questionnaires, extended with additional questions specifically focused on ATLog structure and functionalities. According to the SUS results, most of the experts (74%) evaluated ATLog with grades over 70, indicating high acceptance of its usability. Over half (52%) of the experts rated the additional questions focused on ATLog’s structure and functionalities in the A range (90–100), while 26% rated them in the B range (80–89), showing strong acceptance of the platform for creating and running personalized interactive scenarios with ATs. According to the TAM results, experts gave high grades for both perceived usefulness (44% in the A range) and perceived ease of use (63% in the A range). Full article

(This article belongs to the Special Issue Assistive Technologies in Care and Rehabilitation: Research, Developments, and International Initiatives)

►▼ Show Figures

Figure 1

14 pages, 921 KiB

Open AccessArticle

Interpretable Prediction and Analysis of PVA Hydrogel Mechanical Behavior Using Machine Learning

by Liying Xu, Siqi Liu, Anqi Lin, Zichuan Su and Daxin Liang

Gels 2025, 11(7), 550; https://doi.org/10.3390/gels11070550 - 16 Jul 2025

Abstract

Polyvinyl alcohol (PVA) hydrogels have emerged as versatile materials due to their exceptional biocompatibility and tunable mechanical properties, showing great promise for flexible sensors, smart wound dressings, and tissue engineering applications. However, rational design remains challenging due to complex structure–property relationships involving multiple formulation parameters. This study presents an interpretable machine learning framework for predicting PVA hydrogel tensile strain properties with emphasis on mechanistic understanding, based on a comprehensive dataset of 350 data points collected from a systematic literature review. XGBoost demonstrated superior performance after Optuna-based optimization, achieving R² values of 0.964 for training and 0.801 for testing. SHAP analysis provided unprecedented mechanistic insights, revealing that PVA molecular weight dominates mechanical performance (SHAP importance: 84.94) through chain entanglement and crystallization mechanisms, followed by degree of hydrolysis (72.46) and cross-linking parameters. The interpretability analysis identified optimal parameter ranges and critical feature interactions, elucidating complex non-linear relationships and reinforcement mechanisms. By addressing the “black box” limitation of machine learning, this approach enables rational design strategies and mechanistic understanding for next-generation multifunctional hydrogels. Full article

(This article belongs to the Special Issue Research Progress and Application Prospects of Gel Electrolytes)

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 2000.

Go to page 1 2 3 4 5

Search Results (120,248)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI