Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (5,856)

Search Parameters:
Keywords = online learning

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
19 pages, 11951 KiB  
Article
A Novel Hybrid Attention-Based RoBERTa-BiLSTM Model for Cyberbullying Detection
by Mohammed A. Mahdi, Suliman Mohamed Fati, Mohammed Gamal Ragab, Mohamed A. G. Hazber, Shahanawaj Ahamad, Sawsan A. Saad and Mohammed Al-Shalabi
Math. Comput. Appl. 2025, 30(4), 91; https://doi.org/10.3390/mca30040091 (registering DOI) - 21 Aug 2025
Abstract
The escalating scale and psychological harm of cyberbullying across digital platforms present a critical social challenge, demanding the urgent development of highly accurate and reliable automated detection systems. Standard fine-tuned transformer models, while powerful, often fall short in capturing the nuanced, context-dependent nature [...] Read more.
The escalating scale and psychological harm of cyberbullying across digital platforms present a critical social challenge, demanding the urgent development of highly accurate and reliable automated detection systems. Standard fine-tuned transformer models, while powerful, often fall short in capturing the nuanced, context-dependent nature of online harassment. This paper introduces a novel hybrid deep learning model called Robustly Optimized Bidirectional Encoder Representations from the Transformers with the Bidirectional Long Short-Term Memory-based Attention model (RoBERTa-BiLSTM), specifically designed to address this challenge. To maximize its effectiveness, the model was systematically optimized using the Optuna framework and rigorously benchmarked against eight state-of-the-art transformer baseline models on a large cyberbullying dataset. Our proposed model achieves state-of-the-art performance, outperforming BERT-base, RoBERTa-base, RoBERTa-large, DistilBERT, ALBERT-xxlarge, XLNet-large, ELECTRA-base, DeBERTa-v3-small with an accuracy of 94.8%, precision of 96.4%, recall of 95.3%, F1 − score of 95.8%, and an AUC of 98.5%. Significantly, it demonstrates a substantial improvement in F1 − score over the strongest baseline and reduces critical false negative errors by 43%, all while maintaining moderate computational efficiency. Furthermore, our efficiency analysis indicates that this superior performance is achieved with a moderate computational complexity. The results validate our hypothesis that a specialized hybrid architecture, which synergizes contextual embedding with sequential processing and attention mechanism, offers a more robust and practical solution for real-world social media applications. Full article
Show Figures

Figure 1

23 pages, 5093 KiB  
Article
Reentry Trajectory Online Planning and Guidance Method Based on TD3
by Haiqing Wang, Shuaibin An, Jieming Li, Guan Wang and Kai Liu
Aerospace 2025, 12(8), 747; https://doi.org/10.3390/aerospace12080747 - 21 Aug 2025
Abstract
Aiming at the problem of poor autonomy and weak time performance of reentry trajectory planning for Reusable Launch Vehicle (RLV), an online reentry trajectory planning and guidance method based on Twin Delayed Deep Deterministic Policy Gradient (TD3) is proposed. In view of the [...] Read more.
Aiming at the problem of poor autonomy and weak time performance of reentry trajectory planning for Reusable Launch Vehicle (RLV), an online reentry trajectory planning and guidance method based on Twin Delayed Deep Deterministic Policy Gradient (TD3) is proposed. In view of the advantage that the drag acceleration can be quickly measured by the airborne inertial navigation equipment, the reference profile adopts the design of the drag acceleration–velocity profile in the reentry corridor. In order to prevent the problem of trajectory angle jump caused by the unsmooth turning point of the section, the section form adopts the form of four multiple functions to ensure the smooth connection of the turning point. Secondly, considering the advantages of the TD3 dual Critic network structure and delay update mechanism to suppress strategy overestimation, the TD3 algorithm framework is used to train multiple strategy networks offline and output profile parameters. Finally, considering the reentry uncertainty and the guidance error caused by the limitation of the bank angle reversal amplitude during lateral guidance, the networks are invoked online many times to solve the profile parameters in real time and update the profile periodically to ensure the rapidity and autonomy of the guidance command generation. The TD3 strategy networks are trained offline and invoked online many times so that the cumulative error in the previous guidance period can be eliminated when the algorithm is called again each time, and the online rapid generation and update of the reentry trajectory is realized, which effectively improves the accuracy and computational efficiency of the landing point. Full article
(This article belongs to the Special Issue Flight Guidance and Control)
Show Figures

Figure 1

36 pages, 14078 KiB  
Article
Workload Prediction for Proactive Resource Allocation in Large-Scale Cloud-Edge Applications
by Thang Le Duc, Chanh Nguyen and Per-Olov Östberg
Electronics 2025, 14(16), 3333; https://doi.org/10.3390/electronics14163333 - 21 Aug 2025
Abstract
Accurate workload prediction is essential for proactive resource allocation in large-scale Content Delivery Networks (CDNs), where traffic patterns are highly dynamic and geographically distributed. This paper introduces a CDN-tailored prediction and autoscaling framework that integrates statistical and deep learning models within an adaptive [...] Read more.
Accurate workload prediction is essential for proactive resource allocation in large-scale Content Delivery Networks (CDNs), where traffic patterns are highly dynamic and geographically distributed. This paper introduces a CDN-tailored prediction and autoscaling framework that integrates statistical and deep learning models within an adaptive feedback loop. The framework is evaluated using 18 months of real traffic traces from a production multi-tier CDN, capturing realistic workload seasonality, cache–tier interactions, and propagation delays. Unlike generic cloud-edge predictors, our design incorporates CDN-specific features and model-switching mechanisms to balance prediction accuracy with computational cost. Seasonal ARIMA (S-ARIMA), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Online Sequential Extreme Learning Machine (OS-ELM) are combined to support both short-horizon scaling and longer-term capacity planning. The predictions drive a queue-based resource-estimation model, enabling proactive cache–server scaling with low rejection rates. Experimental results demonstrate that the framework maintains high accuracy while reducing computational overhead through adaptive model selection. The proposed approach offers a practical, production-tested solution for predictive autoscaling in CDNs and can be extended to other latency-sensitive edge-cloud services with hierarchical architectures. Full article
(This article belongs to the Special Issue Next-Generation Cloud–Edge Computing: Systems and Applications)
Show Figures

Graphical abstract

18 pages, 1212 KiB  
Article
Part-Wise Graph Fourier Learning for Skeleton-Based Continuous Sign Language Recognition
by Dong Wei, Hongxiang Hu and Gang-Feng Ma
J. Imaging 2025, 11(8), 286; https://doi.org/10.3390/jimaging11080286 - 21 Aug 2025
Abstract
Sign language is a visual language articulated through body movements. Existing approaches predominantly leverage RGB inputs, incurring substantial computational overhead and remaining susceptible to interference from foreground and background noise. A second fundamental challenge lies in accurately modeling the nonlinear temporal dynamics and [...] Read more.
Sign language is a visual language articulated through body movements. Existing approaches predominantly leverage RGB inputs, incurring substantial computational overhead and remaining susceptible to interference from foreground and background noise. A second fundamental challenge lies in accurately modeling the nonlinear temporal dynamics and inherent asynchrony across body parts that characterize sign language sequences. To address these challenges, we propose a novel part-wise graph Fourier learning method for skeleton-based continuous sign language recognition (PGF-SLR), which uniformly models the spatiotemporal relations of multiple body parts in a globally ordered yet locally unordered manner. Specifically, different parts within different time steps are treated as nodes, while the frequency domain attention between parts is treated as edges to construct a part-level Fourier fully connected graph. This enables the graph Fourier learning module to jointly capture spatiotemporal dependencies in the frequency domain, while our adaptive frequency enhancement method further amplifies discriminative action features in a lightweight and robust fashion. Finally, a dual-branch action learning module featuring an auxiliary action prediction branch to assist the recognition branch is designed to enhance the understanding of sign language. Our experimental results show that the proposed PGF-SLR achieved relative improvements of 3.31%/3.70% and 2.81%/7.33% compared to SOTA methods on the dev/test sets of the PHOENIX14 and PHOENIX14-T datasets. It also demonstrated highly competitive recognition performance on the CSL-Daily dataset, showcasing strong generalization while reducing computational costs in both offline and online settings. Full article
(This article belongs to the Special Issue Advances in Machine Learning for Computer Vision Applications)
Show Figures

Figure 1

20 pages, 11319 KiB  
Article
Enhanced Generalizability of RNA Secondary Structure Prediction via Convolutional Block Attention Network and Ensemble Learning
by Hanbo Lin, Dongyue Hou, Zhaoyite Li, Shuaiqi Wang, Yuchen Liu, Jiajie Gu, Juncheng Qian, Ruining Yin, Hui Zhao, Shaofei Wang, Yuzong Chen, Dianwen Ju and Xian Zeng
Molecules 2025, 30(16), 3447; https://doi.org/10.3390/molecules30163447 - 21 Aug 2025
Abstract
The determination of RNA secondary structure (RSS) could help understand RNA’s functional mechanisms, guiding the design of RNA-based therapeutics, and advancing synthetic biology applications. However, traditional methods such as NMR for determining RSS are typically time-consuming and labor-intensive. As a result, the accurate [...] Read more.
The determination of RNA secondary structure (RSS) could help understand RNA’s functional mechanisms, guiding the design of RNA-based therapeutics, and advancing synthetic biology applications. However, traditional methods such as NMR for determining RSS are typically time-consuming and labor-intensive. As a result, the accurate prediction of RSS remains a fundamental yet unmet need in RNA research. Various deep learning (DL)-based methods achieved improved accuracy over thermodynamic-based methods. However, the over-parameterization nature of DL makes these methods prone to overfitting and thus limits their generalizability. Meanwhile, the inconsistency of RSS predictions between these methods further aggravated the crisis of generalizability. Here, we propose TrioFold to achieve enhanced generalizability of RSS prediction by integrating base-pairing clues learned from both thermodynamic- and DL-based methods by ensemble learning and convolutional block attention mechanism. TrioFold achieves higher accuracy in intra-family predictions and enhanced generalizability in inter-family and cross-RNA-types predictions. Additionally, we have developed an online webserver equipped with widely used RSS prediction algorithms and analysis tools, providing an accessible platform for the RNA research community. This study demonstrated new opportunities to improve generalizability for RSS predictions by efficient ensemble learning of base-pairing clues learned from both thermodynamic- and DL-based algorithms. Full article
Show Figures

Figure 1

32 pages, 4991 KiB  
Article
Attention-Fused Staged DWT-LSTM for Fault Diagnosis of Embedded Sensors in Asphalt Pavement
by Jiarui Zhang, Haihui Duan, Songtao Lv, Dongdong Ge and Chaoyue Rao
Materials 2025, 18(16), 3917; https://doi.org/10.3390/ma18163917 - 21 Aug 2025
Abstract
Fault diagnosis for embedded sensors in asphalt pavement faces significant challenges, including the scarcity of real-world fault data and the difficulty in identifying compound faults, which severely compromises the reliability of monitoring data. To address these issues, this study proposes an intelligent diagnostic [...] Read more.
Fault diagnosis for embedded sensors in asphalt pavement faces significant challenges, including the scarcity of real-world fault data and the difficulty in identifying compound faults, which severely compromises the reliability of monitoring data. To address these issues, this study proposes an intelligent diagnostic framework that integrates a Discrete Wavelet Transform (DWT) with a staged, attention-based Long Short-Term Memory (LSTM) network. First, various fault modes were systematically defined, including short-term (i.e., bias, gain, and detachment), long-term (i.e., drift), and their compound forms. A fine-grained fault injection and labeling strategy was then developed to generate a comprehensive dataset. Second, a novel diagnostic model was designed based on a “Decomposition-Focus-Fusion” architecture. In this architecture, the DWT is employed to extract multi-scale features, and independent sub-models—a Bidirectional LSTM (Bi-LSTM) and a stacked LSTM—are subsequently utilized to specialize in learning short-term and long-term fault characteristics, respectively. Finally, an attention network intelligently weights and fuses the outputs from these sub-models to achieve precise classification of eight distinct sensor operational states. Validated through rigorous 5-fold cross-validation, experimental results demonstrate that the proposed framework achieves a mean diagnostic accuracy of 98.89% (±0.0040) on the comprehensive test set, significantly outperforming baseline models such as SVM, KNN, and a unified LSTM. A comprehensive ablation study confirmed that each component of the “Decomposition-Focus-Fusion” architecture—DWT features, staged training, and the attention mechanism—makes an indispensable contribution to the model’s superior performance. The model successfully distinguishes between “drift” and “normal” states—which severely confuse the baseline models—and accurately identifies various complex compound faults. Furthermore, simulated online diagnostic tests confirmed the framework’s rapid response capability to dynamic faults and its computational efficiency, meeting the demands of real-time monitoring. This study offers a precise and robust solution for the fault diagnosis of embedded sensors in asphalt pavement. Full article
21 pages, 3237 KiB  
Article
ELM-GA-Based Active Comfort Control of a Piggyback Transfer Robot
by Liyan Feng, Xinping Wang, Teng Liu, Kaicheng Qi, Long Zhang, Jianjun Zhang and Shijie Guo
Machines 2025, 13(8), 748; https://doi.org/10.3390/machines13080748 - 21 Aug 2025
Abstract
The improvement of comfort in the human–robot interaction for care recipients is a significant challenge in the development of nursing robots. The existing methods for enhancing comfort largely depend on subjective comfort questionnaires, which are prone to unavoidable errors. Additionally, traditional passive movement [...] Read more.
The improvement of comfort in the human–robot interaction for care recipients is a significant challenge in the development of nursing robots. The existing methods for enhancing comfort largely depend on subjective comfort questionnaires, which are prone to unavoidable errors. Additionally, traditional passive movement control approaches lack the ability to adapt and effectively improve care recipient comfort. To address these problems, this paper proposes an active, personalized intelligent control method based on neural networks. A muscle activation prediction model is established for the piggyback transfer robot, enabling dynamic adjustments during the care process to improve human comfort. Initially, a kinematic analysis of the piggyback transfer robot is conducted to determine the optimal back-carrying trajectory. Experiments were carried out to measure human–robot contact forces, chest holder rotation angles, and muscle activation levels. Subsequently, an Online Sequential Extreme Learning Machine (OS-ELM) algorithm is used to train a predictive model. The model takes the contact forces and chest holder rotation angle as inputs, while outputting the latissimus dorsi muscle activation levels. The Genetic Algorithm (GA) is then employed to dynamically adjust the chest holder’s rotation angle to minimize the difference between actual muscle activation and the comfort threshold. Comparative experiments demonstrate that the proposed ELM-GA-based active control method effectively enhances comfort during the piggyback transfer process, as evidenced by both subjective feedback and objective measurements of muscle activation. Full article
(This article belongs to the Special Issue Vibration Isolation and Control in Mechanical Systems)
Show Figures

Figure 1

18 pages, 2670 KiB  
Article
Score Your Way to Clinical Reasoning Excellence: SCALENEo Online Serious Game in Physiotherapy Education
by Renaud Hage, Frédéric Dierick, Joël Da Natividade, Simon Daniau, Wesley Estievenart, Sébastien Leteneur, Jean-Christophe Servotte, Mark A. Jones and Fabien Buisseret
Educ. Sci. 2025, 15(8), 1077; https://doi.org/10.3390/educsci15081077 - 21 Aug 2025
Abstract
SCALENEo (Smart ClinicAL rEasoning iN physiothErapy) is an innovative online serious game designed to improve clinical reasoning in musculoskeletal physiotherapy education. Adapted from the “Happy Families” card game, it provides an interactive, structured approach to developing students/learners’ ability to categorize clinical information into [...] Read more.
SCALENEo (Smart ClinicAL rEasoning iN physiothErapy) is an innovative online serious game designed to improve clinical reasoning in musculoskeletal physiotherapy education. Adapted from the “Happy Families” card game, it provides an interactive, structured approach to developing students/learners’ ability to categorize clinical information into families of hypotheses. This digital platform supports both self-directed and collaborative learning, eliminating the need for continuous instructor supervision while ensuring meaningful engagement. SCALENEo features a unique feedback and scoring system that not only assesses students/learners’ decision-making processes but also promotes cautious and reflective reasoning over random guessing. By aligning with evidence-based pedagogical strategies, such as serious games and formative assessment, SCALENEo offers educators a powerful tool to reinforce critical thinking, improve student/learner engagement, and facilitate deeper learning in clinical reasoning education. Full article
Show Figures

Figure 1

22 pages, 1805 KiB  
Article
Fault Diagnosis of Wind Turbine Pitch Bearings Based on Online Soft-Label Meta-Learning and Gaussian Prototype Network
by Lianghong Wang, Zhongzhuang Bai, Hongxiang Li, Panpan Yang, Jie Tao, Xuemei Zou, Jinliang Zhao and Chunwei Wang
Energies 2025, 18(16), 4437; https://doi.org/10.3390/en18164437 - 20 Aug 2025
Abstract
Meta-learning has demonstrated significant advantages in small-sample tasks and has attracted considerable attention in wind turbine fault diagnosis. However, due to extreme operating conditions and equipment aging, the monitoring data of wind turbines often contain false alarms or missed detections. This results in [...] Read more.
Meta-learning has demonstrated significant advantages in small-sample tasks and has attracted considerable attention in wind turbine fault diagnosis. However, due to extreme operating conditions and equipment aging, the monitoring data of wind turbines often contain false alarms or missed detections. This results in inaccurate fault sample labeling. In meta-learning, these erroneous labels not only fail to help models quickly adapt to new meta-test tasks, but they also interfere with learning for new tasks, which leads to “negative transfer” phenomena. To address this, this paper proposes a novel method called Online Soft-Labeled Meta-learning with Gaussian Prototype Networks (SL-GPN). During training, the method dynamically aggregates feature similarities across multiple tasks or samples to form online soft labels. They guide model training process and effectively solve small-sample bearing fault diagnosis challenges. Experimental tests on small-sample data under various operating conditions and error labels were carried out. The results show that the proposed method improves diagnostic accuracy in small-sample environments, reduces false alarm rates, and demonstrates excellent generalization performance. Full article
Show Figures

Figure 1

14 pages, 908 KiB  
Brief Report
How Metaphorical Instructions Influence Children’s Motor Learning and Memory in Online Settings
by Weiqi Zheng and Xinyun Liu
Behav. Sci. 2025, 15(8), 1132; https://doi.org/10.3390/bs15081132 - 20 Aug 2025
Abstract
Metaphorical instructions are widely used in motor skill learning, yet their impact on learning and memory processes in children remains underexplored. This study examined whether metaphor-based language could enhance children’s acquisition and recall of body posture-related motor skills in an online learning environment. [...] Read more.
Metaphorical instructions are widely used in motor skill learning, yet their impact on learning and memory processes in children remains underexplored. This study examined whether metaphor-based language could enhance children’s acquisition and recall of body posture-related motor skills in an online learning environment. Forty-eight children aged 7 to 9 were randomly assigned to receive either metaphorical or explicit verbal instructions while learning 15 gymnastic postures demonstrated through static images. Following the learning phase, participants completed a free recall task, in which they reproduced the learned postures without cues, and a recognition task involving the identification of previously learned postures. Results indicated that children in the metaphor group recalled significantly more postures than those in the explicit group, with no reduction in movement quality. However, no group differences were observed in recognition accuracy or discrimination sensitivity. These findings suggest that metaphorical instructions may enhance children’s ability to retrieve self-generated motor representations but offer limited advantage when external cues are available. The study provides evidence for the value of metaphor-based strategies in supporting immediate motor memory in digital, child-focused learning settings and highlights the potential task-dependency of instructional language effects on memory outcomes. Full article
(This article belongs to the Special Issue Physical and Motor Development in Children)
Show Figures

Figure 1

17 pages, 733 KiB  
Article
The Positive Impacts of Tandem Courses: A Case Study on Teacher Motivation and Classroom Engagement
by Marta Maciejasz, Anna Bausova, Irina Bausova, Balazs Horvath, Alina-Georgeta Mag and Alina-Maria Moldovan
Educ. Sci. 2025, 15(8), 1067; https://doi.org/10.3390/educsci15081067 - 20 Aug 2025
Abstract
This article explores the implementation of a tandem course that integrates gamification and interactive teaching methods and investigates how this model affects teacher motivation and participant engagement, particularly in higher education contexts. This study also highlights the potential of tandem teaching beyond its [...] Read more.
This article explores the implementation of a tandem course that integrates gamification and interactive teaching methods and investigates how this model affects teacher motivation and participant engagement, particularly in higher education contexts. This study also highlights the potential of tandem teaching beyond its traditional use in language learning and provides qualitative and quantitative insights into the experiences of both course participants and educators, showing how collaborative, gamified teaching strategies can inspire more effective, student-centered pedagogy. It examines how the course was developed, the outcomes in terms of teachers’ engagement and the enhancement in learning experiences, and proposes a new perspective on how education can be restructured. The study emphasizes that traditional, lecture-based teaching is no longer sufficient in engaging modern learners and teachers too. By adopting more digital, student-centered approaches, we suggest that subjects can be reimagined as more interactive and teacher–student-friendly. The main question stated in the article sounds like the following: “How does gamification and interactive teaching methodologies, like tandem course, affect teacher and participant engagement and motivation?”. To address this question, a study was conducted based on the tandem course titled “Gamification in the learning process and interactive teaching methodologies” prepared within the FORTHEM Alliance by three united universities. It was delivered online during four meetings in May 2024. Full article
(This article belongs to the Section Technology Enhanced Education)
Show Figures

Figure 1

24 pages, 11770 KiB  
Article
Secure Communication and Resource Allocation in Double-RIS Cooperative-Aided UAV-MEC Networks
by Xi Hu, Hongchao Zhao, Dongyang He and Wujie Zhang
Drones 2025, 9(8), 587; https://doi.org/10.3390/drones9080587 - 19 Aug 2025
Abstract
In complex urban wireless environments, unmanned aerial vehicle–mobile edge computing (UAV-MEC) systems face challenges like link blockage and single-antenna eavesdropping threats. The traditional single reconfigurable intelligent surface (RIS), limited in collaboration, struggles to address these issues. This paper proposes a double-RIS cooperative UAV-MEC [...] Read more.
In complex urban wireless environments, unmanned aerial vehicle–mobile edge computing (UAV-MEC) systems face challenges like link blockage and single-antenna eavesdropping threats. The traditional single reconfigurable intelligent surface (RIS), limited in collaboration, struggles to address these issues. This paper proposes a double-RIS cooperative UAV-MEC optimization scheme, leveraging their joint reflection to build multi-dimensional signal paths, boosting legitimate link gains while suppressing eavesdropping channels. It considers double-RIS phase shifts, ground user (GU) transmission power, UAV trajectories, resource allocation, and receiving beamforming, aiming to maximize secure energy efficiency (EE) while ensuring long-term stability of GU and UAV task queues. Given random task arrivals and high-dimensional variable coupling, a dynamic model integrating queue stability and secure transmission constraints is built using Lyapunov optimization, transforming long-term stochastic optimization into slot-by-slot deterministic decisions via the drift-plus-penalty method. To handle high-dimensional continuous spaces, an end-to-end proximal policy optimization (PPO) framework is designed for online learning of multi-dimensional resource allocation and direct acquisition of joint optimization strategies. Simulation results show that compared with benchmark schemes (e.g., single RIS, non-cooperative double RIS) and reinforcement learning algorithms (e.g., advantage actor–critic (A2C), deep deterministic policy gradient (DDPG), deep Q-network (DQN)), the proposed scheme achieves significant improvements in secure EE and queue stability, with faster convergence and better optimization effects, fully verifying its superiority and robustness in complex scenarios. Full article
(This article belongs to the Section Drone Communications)
Show Figures

Figure 1

26 pages, 3443 KiB  
Article
Intelligent Soft Sensors for Inferential Monitoring of Hydrodesulfurization Process Analyzers
by Željka Ujević Andrijić, Srečko Herceg, Magdalena Šimić and Nenad Bolf
Actuators 2025, 14(8), 410; https://doi.org/10.3390/act14080410 - 19 Aug 2025
Abstract
This work presents the development of soft sensor models for monitoring the operation of online process analyzers used to measure the sulfur content in the product of the refinery hydrodesulfurization process. Since sulfur content often fluctuates over time, soft sensor models must account [...] Read more.
This work presents the development of soft sensor models for monitoring the operation of online process analyzers used to measure the sulfur content in the product of the refinery hydrodesulfurization process. Since sulfur content often fluctuates over time, soft sensor models must account for these frequency fluctuations. We have therefore developed dynamic data-driven models based on linear and nonlinear system identification techniques (finite impulse response—FIR, autoregressive with exogenous inputs—ARX, output error—OE, nonlinear ARX—NARX, Hammerstein–Wiener—HW) and machine learning techniques, including models based on long short-term memory (LSTM) and gated recurrent unit (GRU) networks, as well as artificial neural networks (ANNs). The core steps in model development included the selection and preprocessing of continuously measured plant process data, collected from a full-scale industrial hydrodesulfurization unit under normal operating conditions. The developed soft sensor models are intended to support or replace process analyzers during maintenance periods or equipment failures. Moreover, these models enable the application of inferential control strategies, where unmeasured process variables—such as sulfur content—can be estimated in real time and used as feedback for advanced process control. Full article
(This article belongs to the Special Issue Analysis and Design of Linear/Nonlinear Control System)
Show Figures

Figure 1

27 pages, 4676 KiB  
Article
Online Traffic Obfuscation Experimental Framework for the Smart Home Privacy Protection
by Shuping Huang, Jianyu Cao, Ziyi Chen, Qi Zhong and Minghe Zhang
Electronics 2025, 14(16), 3294; https://doi.org/10.3390/electronics14163294 - 19 Aug 2025
Abstract
Attackers can use Ethernet or WiFi sniffers to capture smart home device traffic and identify device events based on packet length and timing characteristics, thereby inferring users’ home behaviors. To address this issue, traffic obfuscation techniques have been extensively studied, with common methods [...] Read more.
Attackers can use Ethernet or WiFi sniffers to capture smart home device traffic and identify device events based on packet length and timing characteristics, thereby inferring users’ home behaviors. To address this issue, traffic obfuscation techniques have been extensively studied, with common methods including packet padding, packet segmentation, and fake traffic injection. However, existing research predominantly utilizes non-real-time traffic to verify whether traffic obfuscation techniques can effectively reduce the recognition rate of traffic analysis attacks on smart home devices. It often overlooks the potential impact of obfuscation operations on device connectivity and functional integrity in real network environments. To address this limitation, an online experimental framework for three fundamental traffic obfuscation techniques is proposed: packet padding, packet segmentation, and fake traffic injection. Experimental results demonstrate that the proposed framework maintains the continuous connectivity and functional integrity of smart home devices with a low system overhead, achieving an average CPU usage rate of less than 0.4% and an average memory occupancy rate of less than 2%. Evaluation results based on the random forest classification method show that the device event recognition accuracy for injected fake traffic exceeds 89%. In this context, a higher recognition accuracy indicates that attackers are more effectively deceived by the injected fake traffic. Conversely, the recognition accuracy for packet padding and packet segmentation methods is nearly zero, and a lower recognition accuracy in these cases implies a more effective implementation of those obfuscation techniques. Further evaluation results based on the deep learning classification method reveal that the packet segmentation approach significantly reduces device recognition accuracy for certain devices to below 5%, while simultaneously increasing the false recognition rate for other devices to over 95%. In contrast, fake traffic injection achieves a device recognition accuracy exceeding 90%. Moreover, the obfuscation effect of the packet padding method is found to be suboptimal, a finding consistent with existing literature suggesting that no single obfuscation technique can effectively withstand all types of traffic analysis attacks. Full article
(This article belongs to the Section Networks)
Show Figures

Figure 1

19 pages, 2268 KiB  
Article
Toward the Implementation of Text-Based Web Page Classification and Filtering Solution for Low-Resource Home Routers Using a Machine Learning Approach
by Audronė Janavičiūtė, Agnius Liutkevičius and Nerijus Morkevičius
Electronics 2025, 14(16), 3280; https://doi.org/10.3390/electronics14163280 - 18 Aug 2025
Viewed by 85
Abstract
Restricting and filtering harmful content on the Internet is a serious problem that is often addressed even at the state and legislative levels. Existing solutions for restricting and filtering online content are usually installed on end-user devices and are easily circumvented and difficult [...] Read more.
Restricting and filtering harmful content on the Internet is a serious problem that is often addressed even at the state and legislative levels. Existing solutions for restricting and filtering online content are usually installed on end-user devices and are easily circumvented and difficult to adapt to larger groups of users with different filtering needs. To mitigate this problem, this study proposed a model of a web page classification and filtering solution suitable for use on home routers or other low-resource web page filtering devices. The proposed system combines the constantly updated web page category list approach with machine learning-based text classification methods. Unlike existing web page filtering solutions, such an approach does not require additional software on the client-side, is more difficult to circumvent for ordinary users and can be implemented using common low-resource routers intended for home and organizations usage. This study evaluated the feasibility of the proposed solution by creating the less resource-demanding implementations of machine learning-based web page classification methods adapted for low-resource home routers that could be used to classify and filter unwanted Internet pages in real-time based on the text of the page. The experimental evaluation of softmax regression, decision tree, random forest, and linear SVM (support vector machine) machine learning methods implemented in the C/C++ programming language was performed using a commercial home router Asus RT-AC85P with 256 MB RAM (random access memory) and MediaTek MT7621AT 880 MHz CPU (central processing unit). The implementation of the linear SVM classifier demonstrated the best accuracy of 0.9198 and required 1.86 s to process a web page. The random forest model was only slightly faster (1.56 s to process a web page), while its accuracy reached only 0.7879. Full article
Show Figures

Figure 1

Back to TopTop