Search Results (1,484)

Sentiment analysis methods for interactive services such as Danmu in online videos are challenged by their colloquial style and diverse sentiment expressions. For instance, the existing methods cannot easily distinguish between similar sentiments. To address these limitations, this paper proposes a dual-channel model integrated with attention mechanisms for multi-dimensional sentiment analysis of Danmu. First, we replace word embeddings with character embeddings to better capture the colloquial nature of Danmu text. Second, the dual-channel multi-dimensional sentiment encoder extracts both the high-level semantic and raw contextual information. Channel I of the encoder learns the sentiment features from different perspectives through a mixed model that combines the benefits of self-Attention and Dilated CNN (ADCMix) and performs contextual modeling through bidirectional long short-term memory (BiLSTM) with attention mechanisms. Channel II mitigates potential biases and omissions in the sentiment features. The model combines the two channels to erase the fuzzy boundaries between similar sentiments. Third, a multi-dimensional sentiment decoder is designed to handle the diversity in sentiment expressions. The superior performance of the proposed model is experimentally demonstrated on two datasets. Our model outperformed the state-of-the-art methods on both datasets, with improvements of at least 2.05% in accuracy and 3.28% in F1-score. Full article

Compared to 4G long-term evolution (LTE) networks, 5G and 6G networks provide fast data transmission with little delay, larger base station capacity, enhanced quality of service (QoS), and extensive multiple-input-multiple-output (MIMO) channels. Nevertheless, the attainment of mobility and handover (HO) in 5/6G networks has been hindered by substantial changes in intelligent devices and the high-definition applications of multimedia. Therefore, the existing cellular network is compared with difficulties in transmitting large amounts of data at a faster rate, ensuring high QoS, minimizing latency, and efficiently managing HOs and mobility. This paper primarily addresses the difficulties related to HO and mobility management in 5G/6G networks. The findings of this paper emphasize the importance of aligning mobility and HO strategies with sustainable development goals to reduce energy consumption and improve resource allocation. It focuses on integrating innovative technologies such as artificial intelligence and machine learning to enhance the sustainability and efficiency of mobility and HO management. The paper provides a comprehensive analysis of the current body of the literature and explores essential metrics for measuring performance (known as KPIs) and potential solutions for difficulties linked to HO and mobility. The analysis takes into account established standards in the field. Furthermore, it assesses the effectiveness of existing models in dealing with HO and mobility management problems, considering criteria such as energy efficiency, dependability, latency, and scalability. This survey concludes by highlighting key challenges associated with HO and mobility management in existing research models. It also offers comprehensive assessments of the proposed solutions, accompanied by suggestions for future research. Full article

The use of agrochemicals in agriculture is widespread globally, as it enables increased crop yields. However, they also contain heavy metals such as copper and nickel, which can leach into the drinking water and harm the environment and human health. As such, it is imperative that they are removed from drinking water. One way to achieve this is through adsorption using biosorbents. This proof-of-concept study aimed to synthesize and characterize environmentally friendly hydrogels from sodium alginate (SA) and pomegranate peel powder (PPP). The gels were characterized using Fourier-Transform Infrared Spectroscopy (FTIR), Scanning Electron Microscopy (SEM), and water uptake tests. The FTIR analysis confirmed the presence of the expected functional groups, SEM revealed that incorporating PPP enhanced the roughness and porosity of the gels, and gels with PPP incorporation were able to absorb 1.58 times more water than SA-only gels. Moreover, their ability to remediate copper and nickel from contaminated water was tested. Here, the effects of contact time, pH, and adsorbent amount were tested for copper, demonstrating that the optimal contact time was 60 min, the optimal pH was ~5, and 0.01 g of adsorbent was needed for optimal adsorption. The effect of contact time was tested for nickel, and it was found that the optimal contact time was 5 min. Overall, these gels show promising results for the remediation of copper and nickel from contaminated water. Full article

Rheumatoid arthritis (RA) is a chronic autoimmune disease marked by joint inflammation and progressive disability. While biological disease-modifying antirheumatic drugs (bDMARDs) have significantly improved disease control, predicting individual treatment response remains clinically challenging. This study presents a machine learning approach to predict 12-month disease activity, measured by DAS28-CRP, in RA patients beginning bDMARD therapy. We trained and evaluated eight regression models, including Ridge, Lasso, Support Vector Regression, and XGBoost, using baseline clinical features from 154 RA patients treated at University Hospital Erlangen. A rigorous nested cross-validation strategy was applied for internal model selection and validation. Importantly, model generalizability was assessed using an independent external dataset from the Austrian BioReg registry, which includes a more diverse, real-world RA patient population from across multiple clinical sites. The Ridge regression model achieved the best internal performance (MAE: 0.633, R²: 0.542) and showed strong external validity when applied to unseen BioReg data (MAE: 0.678, R²: 0.491). These results indicate robust cross-cohort generalization. By predicting continuous DAS28-CRP scores instead of binary remission labels, our approach supports flexible, individualized treatment planning based on local or evolving clinical thresholds. This work demonstrates the feasibility and clinical value of externally validated, data-driven tools for precision treatment planning in RA. Full article

This study examines the diversity of terminologies associated with assistive technology (AT), a crucial field that promotes autonomy and inclusion for people with disabilities. Although the wide use of assistive technology is observed in the literature, a variety of terms are often used interchangeably, which hinders research, technological development, and the formulation of public policies. In this sense, this systematic review aimed to identify, categorise, and analyse the diversity of terms used to describe AT in the scientific literature, contributing to greater conceptual clarity and supporting structured and interdisciplinary development in the field. A comprehensive search was conducted in July 2024 across the Scopus, Web of Science, and PubMed databases, covering publications from 1989 to 2024. Eligible studies were peer-reviewed journal articles in English that conceptually defined at least one AT-related term. The selection process followed the PRISMA 2020 guidelines and included studies from Q1 and Q2 journals to ensure academic rigour. A total of 117 studies were included out of 11,941 initial records. Sixteen distinct terms were identified and grouped into five clusters based on semantic and functional similarities: Cluster 1—Technologies for assistance and inclusion. Cluster 2—Functional assistive devices. Cluster 3—Assistive interaction interfaces. Cluster 4—Assistive environmental technologies. Cluster 5—Assistive systems. A complementary meta-analysis revealed geographic and temporal trends, indicating that terms such as “assistive technology” and “assistive device” are globally dominant. In contrast, others, like “enabling technology,” are more context-specific and emerging. The findings contribute theoretically by providing a structured framework for understanding AT terminology and practically by supporting the design of public policy and interdisciplinary communication. Full article

Wireless sensor networks have become a vital technology that is extensively applied across multiple industries, including agriculture, industrial operations, and smart cities, as well as residential smart homes and environmental monitoring systems. Security threats emerge in these systems through hidden routing-level attacks such as Wormhole and Sinkhole attacks. The aim of this research was to develop a methodology for detecting security incidents in WSNs by conducting real-time analysis of Wormhole and Sinkhole attacks. Furthermore, the paper proposes a novel detection methodology combined with architectural enhancements to improve network robustness, measured by hop counts, delays, false data ratios, and route integrity. A real-time WSN infrastructure was developed using ZigBee and Global System for Mobile Communications/General Packet Radio Service (GSM/GPRS) technologies. To realistically simulate Wormhole and Sinkhole attack scenarios and conduct evaluations, we developed a modular cyber–physical architecture that supports real-time monitoring, repeatability, and integration of ZigBee- and GSM/GPRS-based attacker nodes. During the experimentation, Wormhole attacks caused the hop count to decrease from 4 to 3, while the average delay increased by 40%, and false sensor readings were introduced in over 30% of cases. Additionally, Sinkhole attacks led to a 27% increase in traffic concentration at the malicious node, disrupting load balancing and route integrity. The proposed multi-stage methodology includes data collection, preprocessing, anomaly detection using the 3-sigma rule, and risk-based decision making. Simulation results demonstrated that the methodology successfully detected route shortening, packet loss, and data manipulation in real time. Thus, the integration of anomaly-based detection with ZigBee and GSM/GPRS enables a timely response to security threats in critical WSN deployments. Full article

Accurately predicting the ionosphere’s Total Electron Content (TEC) is significant for ensuring the regular operation of satellite navigation and communication systems and space weather prediction. To further improve the accuracy of TEC prediction, this paper proposes a TEC prediction model based on the grid-optimized Gate Recurrent Unit (GRU). This model has the following main features: (1) it uses statistical learning methods to interpolate the missing data of TEC observations; (2) it constructs a sliding time window by using the multi-dimensional time series features of two types of solar activity indices to support modeling; (3) It adopts grid search combined with optimization of network depth, time step length, and other hyperparameters to significantly enhance the model’s ability to extract the characteristics of the ionospheric 11-year cycle and seasonal variations. Taking the EGLIN station as an example, the proposed model is verified. The experimental results show that the root mean square error of the GRU model during the period from 2019 to 2020 was 0.78 TECU, which was significantly lower than those of the CCIR, URSI, and statistical machine learning models. Compared with the other three models, the RMSE error of the GRU model was reduced by 72.73%, 72.64%, and 57.38%, respectively. The above research verifies the advantages of the proposed model in predicting TEC and provides a new idea for ionospheric modeling. Full article

Smart walking aids represent a growing trend in assistive technologies designed to support individuals with mobility impairments in their daily lives and rehabilitation. Previous research has introduced sensor-integrated systems that provide user feedback to enhance safety and functional mobility. However, a comprehensive overview of their technological and functional characteristics is lacking. To address this gap, this scoping review systematically mapped the current state of research in sensor-based walking aids, focusing on device types, sensor technologies, application contexts, target populations, and reported outcomes. In addition, integrated artificial intelligence (AI)-based approaches for functional support and health monitoring were examined. Following PRISMA-ScR guidelines, 35 peer-reviewed articles were identified from three databases: ACM Digital Library, IEEE Xplore, and Web of Science. Extracted data were thematically analyzed and synthesized across device types (e.g., walking canes, crutches, walkers, rollators) and use cases, including gait training, fall prevention, and daily support. Findings show that, while many prototypes show promising features, few have been evaluated in clinical settings or over extended periods. A lack of standardized methods for sensor location assessment, often the superficial implementation of feedback modalities, and limited integration with other assistive technologies were identified. In addition, system validation and user testing lack consensus, with few long-term studies and often incomplete demographic data. Diversity in data communication approaches and the heterogeneous use of AI algorithms were also notable. The review highlights key challenges and research opportunities to guide the future development of intelligent, user-centered mobility systems. Full article

This study presents a wearable haptic feedback system designed to support speech training for individuals with speech and hearing impairments. The system provides real-time tactile cues based on detected phonemes, helping users correct their pronunciation independently. Unlike prior approaches focused on passive reception or therapist-led instruction, our method enables active, phoneme-level feedback using a multimodal interface combining audio input, visual reference, and spatially mapped vibrotactile output. We validated the system through three user studies measuring pronunciation accuracy, phoneme discrimination, and learning over time. The results show a significant improvement in word articulation accuracy and user engagement. These findings highlight the potential of real-time haptic pronunciation tools as accessible, scalable aids for speech rehabilitation and second-language learning. Full article

In recent years, researchers have become increasingly interested in identifying traits of cognitive impairment using audio from neuropsychological tests. Unfortunately, there is no universally accepted terminology system that can be used to describe language impairment, and considerable variability exists between clinicians, making detection particularly challenging. Furthermore, databases commonly used by the scientific community present sparse or unbalanced data, which hinders the optimal performance of machine learning models. Therefore, this study aims to test a new methodology for augmenting text data from neuropsychological tests in the Pitt Corpus database to increase classification and interpretability results. The proposed method involves augmenting text data with symptoms commonly present in subjects with cognitive impairment. This innovative approach has enabled us to differentiate between two groups in the database better than widely used text augmentation techniques. The proposed method yielded an increase in the metrics, achieving 0.8742 accuracy, 0.8744 F1-score, 0.8736 precision, and 0.8781 recall. It is shown that implementing large language models with commonly observed symptoms in the language of patients with cognitive impairment in text augmentation can improve the results in low-resource scenarios. Full article

Hospital in the Home (HITH) programs are emerging as a key pillar of smart city healthcare infrastructure, leveraging technology to extend care beyond traditional hospital walls. The global healthcare sector has been conceptualizing the notion of a care without walls hospital, also called HITH, where virtual care takes precedence to address the multifaceted needs of an increasingly aging population grappling with a substantial burden of chronic disease. HITH programs have the potential to significantly reduce hospital bed occupancy, enabling hospitals to better manage the ever-increasing demand for inpatient care. Although many health providers and hospitals have established their own HITH programs, there is a lack of research that provides healthcare executives and HITH program managers with management models and frameworks for such initiatives. There is also a lack of research that provides strategies for improving HITH management in the health sector. To fill this gap, the current study ran a systematic literature review to explore state-of-the-art with regard to this topic. Out of 2631 articles in the pool of this systematic review, 20 articles were deemed to meet the eligibility criteria for the study. After analyzing these studies, nine management models were extracted, which were then categorized into three categories, namely, governance models, general models, and virtual models. Moreover, this study found 23 strategies and categorized them into five groups, namely, referral support, external support, care model support, technical support, and clinical team support. Finally, implications of findings for practitioners are carefully provided. These findings provide healthcare executives and HITH managers with practical frameworks for selecting appropriate management models and implementing evidence-based strategies to optimize program effectiveness, reduce costs, and improve patient outcomes while addressing the growing demand for home-based care. Full article

(1) Virtual reality (VR) technologies have shown significant potential for diagnosing and treating vision-related impairments. This rapid review evaluates and characterizes the existing literature on VR technologies for diagnosing and treating vision-based diseases. (2) Methods: A systematic search was conducted across Ovid MEDLINE, Ovid Embase, the Cochrane Database of Systematic Reviews (Ovid), and the Cochrane Central Register of Controlled Trials (Ovid). Abstracts were screened using Rayyan QCRI, followed by full-text screening and data extraction. Eligible studies were published in peer-reviewed journals, written in English, focused on human participants, used immersive and portable VR devices as the primary intervention, and reported on the clinical effectiveness of VR for therapeutic, diagnostic, or screening purposes for vision or auditory–visual impairments. Various study characteristics, including design and participant details, were extracted, and the MMAT assessment tool was used to evaluate study quality. (3) Results: Seventy-six studies met the inclusion criteria. Among these, sixty-four (84.2%) were non-randomized studies exploring VR’s effectiveness, while twenty-two (15.8%) were randomized-controlled trials. Of the included studies, 38.2% focused on diagnosing, 21.0% on screening, and 38.2% on treating vision impairments. Glaucoma and amblyopia were the most commonly studied visual impairments. (4) Conclusions: The use of standalone, remotely controlled VR headsets for screening and diagnosing visual diseases represents a promising advancement in ophthalmology. With ongoing technological developments, VR has the potential to revolutionize eye care by improving accessibility, efficiency, and personalization. Continued research and innovation in VR applications for vision care are expected to further enhance patient outcomes. Full article

The proliferation of social media has paradoxically facilitated the widespread dissemination of fake news, impacting individuals, politics, economics, and society as a whole. Despite the increasing scholarly research on this phenomenon, a significant gap exists regarding its dynamics in developing countries, particularly how predictors of fake news sharing interact, rather than merely their net effects. To acquire a more nuanced understanding of fake news sharing behavior, we propose identifying the direct and complex interplay among key variables by utilizing a dual analytical framework, leveraging Structural Equation Modeling (SEM) for linear relationships and Fuzzy-Set Qualitative Comparative Analysis (fsQCA) to uncover asymmetric patterns. Specifically, we investigate the influence of news-find-me orientation, social media trust, information-sharing tendencies, and status-seeking motivation on the propensity of fake news sharing behavior. Additionally, we delve into the moderating influence of social media literacy on these observed effects. Based on a cross-sectional survey of 1028 Haitian social media users, the SEM analysis revealed that news-find-me perception had a negative but statistically insignificant influence on fake news sharing behavior. In contrast, information sharing exhibited a significant negative association. Trust in social media was positively and significantly linked to fake news sharing behavior. Meanwhile, status-seeking motivation was positively associated with fake news sharing behavior, although the association did not reach statistical significance. Crucially, social media literacy moderated the effects of trust and information sharing. Interestingly, fsQCA identified three core configurations for fake news sharing: (1) low status seeking, (2) low information-sharing tendencies, and (3) a unique interaction of low “news-find-me” orientation and high social media trust. Furthermore, low social media literacy emerged as a direct core configuration. These findings support the urgent need to prioritize social media literacy as a key intervention in combating the dissemination of fake news. Full article

This article addresses the task of building personalized educational recommendations based on a heterogeneous knowledge graph that integrates data from university curricula, job vacancies, and online courses. To solve the problem of course recommendations by their relevance to a user’s competencies, a graph neural network (GNN)-based approach is proposed, specifically utilizing and comparing the Heterogeneous Graph Transformer (HGT) architecture, Graph Sample and Aggregate network (GraphSAGE), and Heterogeneous Graph Attention Network (HAN). Experiments were conducted on a heterogeneous graph comprising various node and relation types. The models were evaluated using regression and ranking metrics. The results demonstrated the superiority of the HGT-based recommendation model as a link regression task, especially in terms of ranking metrics, confirming its suitability for generating accurate and interpretable recommendations in educational systems. The proposed approach can be useful for developing adaptive learning recommendations aligned with users’ career goals. Full article

This study investigates the impact of Time-of-Use (TOU) scheduling and battery energy storage systems (BESS) on voltage stability in a typical Malaysian medium-voltage distribution network with high photovoltaic (PV) system penetration. The analyzed network comprises 110 nodes connected via eight feeders to a pair of 132/11 kV, 15 MVA transformers, supplying a total load of 20.006 MVA. Each node is integrated with a 100 kW PV system, enabling up to 100% PV penetration scenarios. A hybrid mitigation strategy combining TOU-based load shifting and BESS was implemented to address voltage violations occurring, particularly during low-load night hours. Dynamic simulations using DIgSILENT PowerFactory were conducted under worst-case (no load and peak load) conditions. The novelty of this research is the use of real rural network data to validate a hybrid BESS–TOU strategy, supported by detailed sensitivity analysis across PV penetration levels. This provides practical voltage stabilization insights not shown in earlier studies. Results show that at 100% PV penetration, TOU or BESS alone are insufficient to fully mitigate voltage drops. However, a hybrid application of 0.4 MWh BESS with 20% TOU load shifting eliminates voltage violations across all nodes, raising the minimum voltage from 0.924 p.u. to 0.951 p.u. while reducing active power losses and grid dependency. A sensitivity analysis further reveals that a 60% PV penetration can be supported reliably using only 0.4 MWh of BESS and 10% TOU. Beyond this, hybrid mitigation becomes essential to maintain stability. The proposed solution demonstrates a scalable approach to enable large-scale PV integration in dense rural grids and addresses the specific operational characteristics of Malaysian networks, which differ from commonly studied IEEE test systems. This work fills a critical research gap by using real local data to propose and validate practical voltage mitigation strategies. Full article