Search Results (1,330)

Concrete materials are vulnerable to various sorts of structural defects. Reliable measurement and quantification of concrete defects are crucial for ensuring safety and effective maintenance. Deep learning is commonly utilized to detect and classify concrete defects efficiently. However, most available studies do not study multi-class defect identification. This study aims to develop a multi-class concrete defect detection framework to enhance concrete classification accuracy while enabling reliable defect localization. To achieve this, a new image-based non-destructive measurement dataset comprising 2029 images of concrete defects, categorized into five categories, has been compiled. For defect identification, the DenseNet201 model is modified by adding a guided semantic–spatial fusion module with a squeeze-and-excitation architecture, which enhances feature representation and introduces attention mechanisms to the model, enabling it to detect and track defect regions. Experiments are conducted on the collected dataset, and various scenarios and comparisons are performed to verify the proposed model. Results reveal the superiority of the proposed architecture with an accuracy enhancement of 5.6% compared to the original DenseNet201. A graphical user interface is also designed to integrate the trained model into a practical measurement instrument, enabling users to interact with the backend model and detect various defects from intact cases. Full article

Temporary agency work (TAW) has expanded globally as organizations seek flexibility amid skill shortages and demand volatility. In 2015 the United Nations recognized ‘decent work’ as Sustainable Development Goal (SDG 8), emphasizing sustainable economic growth, fair employment opportunities accessible to all without discrimination, environmental responsibility, and social inclusiveness. This study examines why user organizations (clients) adopt TAW and how these drivers materialize in stakeholder practices that align—or fail to align—with SDG-8 dimensions of decent work. Within a qualitative-dominant, explanatory sequential mixed-methods case study, documentary and statistical analyses were combined with 19 semi-structured interviews across agencies, clients, agency workers, trade unions, and relevant authorities. Inductive thematic analysis identified seven demand-side driver categories and assessed their effects using the SDG-8 pillars as an analytical lens (employment creation, rights at work, social protection, social dialogue). Findings indicate that TAW is primarily deployed to buffer volatility and labour shortages, accelerate hiring, and shift HR administration and parts of risk to agencies, with limited integration of SDG-8–consistent practices. Three cross-cutting gaps emerged: (i) social dialogue is narrow and compliance-oriented, with little strategic focus on decent-work outcomes; (ii) agency-worker voice and representation are weak, and agencies are not consistently recognised as social partners; and (iii) social-sustainability efforts are sparse and ad hoc, with few structured measures for skill development, equal treatment, or clear conversion pathways, while environmentally friendly initiatives are almost completely absent. In Slovenia, TAW fills systemic labour gaps but remains weakly integrated with SDG-8 practices. The study links demand-side drivers to specific decent-work shortfalls and proposes a multi-level policy roadmap—regulatory, industry, TAW agency, and social-dialogue platforms—to advance progress toward social sustainability and environmental responsibility. Full article

Point-of-Interest (POI) recommendation predicts users’ future check-ins based on their historical trajectories and plays a key role in location-based services (LBS). Traditional approaches such as collaborative filtering and matrix factorization model user–POI interaction matrices fail to fully leverage spatio-temporal information and semantic attributes, leading to weak performance on sparse and long-tail POIs. Recently, Graph Neural Networks (GNNs) have been applied by constructing heterogeneous user–POI graphs to capture high-order relations. However, they still struggle to effectively integrate spatio-temporal and semantic information and enhance the discriminative power of learned representations. To overcome these issues, we propose Spatio-Temporal and Semantic Dual-Channel Contrastive Alignment for POI Recommendation (S²DCRec), a novel framework integrating spatio-temporal and semantic information. It employs hierarchical relational encoding to capture fine-grained behavioral patterns and high-level semantic dependencies. The model jointly captures user–POI interactions, temporal dynamics, and semantic correlations in a unified framework. Furthermore, our alignment strategy ensures micro-level collaborative and spatio-temporal consistency and macro-level semantic coherence, enabling fine-grained embedding fusion and interpretable contrastive learning. Experiments on real-world datasets, Foursquare NYC, and Yelp, show that S²DCRec outperforms all baselines, improving F1 scores by 4.04% and 3.01%, respectively. These results demonstrate the effectiveness of the dual-channel design in capturing both sequential and semantic dependencies for accurate POI recommendation. Full article

This paper introduces a novel framework for sensory representation of brain imaging data, combining deep learning-based segmentation with multimodal visual and auditory outputs. Structural magnetic resonance imaging (MRI) predictions are converted into color-coded maps and stereophonic/MIDI sonifications, enabling intuitive interpretation of cortical activation patterns. High-precision U-Net models efficiently generate these outputs, supporting clinical decision-making, cognitive research, and creative applications. Spatial, intensity, and anomalous features are encoded into perceivable visual and auditory cues, facilitating early detection and introducing the concept of “auditory biomarkers” for potential pathological identification. Despite current limitations, including dataset size, absence of clinical validation, and heuristic-based sonification, the pipeline demonstrates technical feasibility and robustness. Future work will focus on clinical user studies, the application of functional MRI (fMRI) time-series for dynamic sonification, and the integration of real-time emotional feedback in cinematic contexts. This multisensory approach offers a promising avenue for enhancing the interpretability of complex neuroimaging data across medical, research, and artistic domains. Full article

Research in “cybertherapy” has explored innovative ways to integrate new technologies as innovative tools in psychological treatment, such as virtual reality. Avatars, as digital representations of users within virtual environments, represent an interesting tool for psychotherapists: they could be used to assess aspects of patients’ self-representations (assessment), to promote behavioral change based on an alternative self-image (treatment), or to exercise therapists’ skills in diagnosis and assessment (formation). Yet, the use of avatars in psychotherapy is still not widespread. In the present study, 77 certified psychotherapists evaluated the three possible uses of avatars described above in terms of technology acceptance model (TAM) factors: perceived usefulness, perceived ease of use and intention-to-use. Partially confirming the TAM, the results show that perceived usefulness in particular is an effective predictor of intention to use avatars in psychotherapy for all three possible uses. Attitudes towards avatars as a psychotherapeutic tool were slightly influenced by mental health professionals’ methodological approach, with cognitive-behavioral psychotherapists showing more positive attitudes towards avatars as a training tool. On the other hand, previous experiences with other technologies (e.g., conducting therapy online or not) affected the perception of avatars’ ease of use as a treatment tool. The present study contributes to identifying factors that influence mental health professionals’ attitudes towards technological innovations in the psychotherapy profession, giving directions for future research in cybertherapy adoption. Full article

The assessment of Chinese text readability plays a significant role in Chinese language education. Due to the intrinsic differences between alphabetic languages and Chinese character representations, the readability assessment becomes more challenging in terms of the language’s inherent complexity in vocabulary, syntax, and semantics. The article proposed the conceptual analogy between Chinese readability assessment and music’s rhythm and tempo patterns, in which the syntactic structures of the Chinese sentences could be transformed into an image. The Chinese Knowledge and Information Processing Tagger (CkipTagger) tool developed by Sinica-Taiwan is utilized to decompose the Chinese text into a set of tokens. These tokens are then refined through a user-defined token pool to retain meaningful units. An image with part-of-speech (POS) information will be generated by using the token versus syntax alignment. A discrete cosine transform (DCT) is then applied to extract the temporal characteristics of the text. Moreover, the study integrated four categories: linguistic features–type–token ratio, average sentence length, total word, and difficulty level of vocabulary for the readability assessment. Finally, these features were fed into the Support Vector Machine (SVM) network for the classifications. Furthermore, a bidirectional long short-term memory (Bi-LSTM) network is adopted for quantitative comparisons. In simulation, a total of 774 Chinese texts fitted with Taiwan Benchmarks for the Chinese Language were selected and graded by Chinese language experts, consisting of equal amounts of basic, intermediate, and advanced levels. The finding indicated the proposed POS with the linguistic features work well in the SVM network, and the performance matches with the more complex architectures like the Bi-LSTM network in Chinese readability assessments. Full article

Sequential recommendation aims to model evolving user preferences based on historical interactions. Transformer-based architectures have achieved strong performance by focusing on user-level sequential patterns, yet global item–item relationships are often underrepresented, limiting the ability to capture broader contextual signals. In many real-world scenarios, items contain rich textual attributes such as descriptions and categories, but these semantic features are seldom exploited in existing sequential models. To address this gap, a Semantic-Aware Global Graph-Enhanced Sequential Recommendation framework (SAGERec) is developed, in which globally derived semantic structures are incorporated to enrich item representations before sequence modeling. Large language models (LLMs) are used to generate semantically grounded item embeddings, from which a global item–item graph is constructed to capture content-level relations that extend beyond behavioral co-occurrence. These semantic relations are further refined through an adaptive edge-weight learning mechanism, enabling the graph structure to align with evolving item representations during training. The adaptively enhanced item embeddings are subsequently integrated into a lightweight Transformer-based sequential encoder for next-item prediction. Extensive experiments on three benchmark datasets demonstrate that the proposed framework consistently outperforms competitive baselines, indicating that integrating LLM-derived semantics with adaptive graph refinement leads to more expressive sequential representations. Full article

The steady-state visual evoked potential (SSVEP), a non-invasive EEG modality, is a prominent approach for brain–computer interfaces (BCIs) due to its high signal-to-noise ratio and minimal user training. However, its practical utility is often hampered by susceptibility to noise, artifacts, and concurrent brain activities, complicating signal decoding. To address this, we propose a novel hybrid deep learning model that integrates a multi-channel restricted Boltzmann machine (RBM) with a convolutional neural network (CNN). The framework comprises two main modules: a feature extraction module and a classification module. The former employs a multi-channel RBM to unsupervisedly learn latent feature representations from multi-channel EEG data, effectively capturing inter-channel correlations to enhance feature discriminability. The latter leverages convolutional operations to further extract spatiotemporal features, constructing a deep discriminative model for the automatic recognition of SSVEP signals. Comprehensive evaluations on multiple public datasets demonstrate that our proposed method achieves competitive performance compared to various benchmarks, particularly exhibiting superior effectiveness and robustness in short-time window scenarios. Full article

Next Point-of-Interest (POI) recommendation is a crucial task in personalized location-based services, aiming to predict the next POI that a user might visit based on their historical trajectories. Although sequence models and Graph Neural Networks (GNNs) have achieved significant success, they often overlook the diversity and dynamics of user preferences. To address these issues, researchers have begun to employ Hypergraph Convolutional Networks (HGCNs) for disentangled representation learning. However, two critical problems have received less attention: (1) the limited expressive capacity of conventional hypergraph convolution layers, which restricts the modeling of complex nonlinear user–POI preference interactions and consequently weakens generalization performance, and (2) the inadequate utilization of contrastive learning mechanisms, which prevents fully capturing cross-view collaborative signals and limits the exploitation of complementary multi-view information. To tackle these challenges, we propose a Nonlinear Enhanced Disentangled Contrastive Hypergraph Learning (NE-DCHL) for next POI recommendation. The proposed model enhances nonlinear modeling capability and generalization by integrating ReLU activation, residual connections, and dropout regularization within the hypergraph convolution layer. A K-Nearest Neighbor (KNN)-based weighted adjacency matrix is employed to construct the geographical-view hypergraph, reducing computational complexity while maintaining essential spatial correlations. Moreover, a mini-batch InfoNCE loss and the GRACE (deep GRAph Contrastive rEpresentation learning) framework are utilized to improve efficiency and cross-view collaboration. Extensive experiments on two real-world datasets demonstrate that NE-DCHL consistently outperforms the original DCHL and other state-of-the-art approaches. Full article

Online reviews on platforms such as Google Maps strongly influence consumer decisions. However, aggregated ratings mask nuanced opinions about specific aspects such as food, drinks, service, lounge, and price. This study presents a multi-aspect sentiment analysis framework for Arabic café reviews. Specifically, we combine machine learning (Linear SVC, Naïve Bayes, Logistic Regression, Decision Tree, Random Forest) and a Convolutional Neural Network (CNN) to perform aspect identification and sentiment classification. A rigorous preprocessing and feature-engineering with TF-IDF and n-gram was implemented and statistically validated through bootstrap confidence intervals and Friedman–Nemenyi significance tests. Experimental results demonstrate that Linear SVC with optimized TF-IDF tri-grams achieved a macro-F1 of 0.89 for aspect identification and 0.71 for sentiment classification. Meanwhile, the CNN model yielded a comparable F1 of 0.89 for aspect identification and a higher 0.76 for sentiment classification. The findings highlight that effective feature representation and model selection can substantially improve Arabic opinion mining. The proposed framework provides a reliable foundation for analyzing Arabic user feedback on location-based platforms and supports more interpretable and data-driven business insights. These insights are essential to enhance personalized recommendations and business intelligence in the hospitality sector. Full article

Understanding and improving web performance is essential for enhancing user experience, yet existing approaches remain largely correlation-based and lack causal interpretability. To address this limitation, we propose a causal-inference-driven framework for diagnosing and optimizing user-centric Web Vitals such as Largest Contentful Paint (LCP), First Input Delay (FID), and Cumulative Layout Shift (CLS). Our contributions are threefold. (1) We construct a comprehensive feature representation that captures Document Object Model (DOM) structure, resource loading behaviors, rendering characteristics, and JavaScript execution, integrating browser-level domain knowledge into the modeling pipeline. (2) We introduce a hybrid causal discovery method that combines constraint-based reasoning with differentiable score-based learning to estimate high-dimensional causal structures reflecting real rendering processes. (3) We develop a causal-effect-based intervention optimization module that leverages counterfactual reasoning to identify actionable modifications for performance improvement. Our framework further leverages structural symmetries inherent in rendering processes, using repeated layout patterns and invariant dependency flows to reduce redundancy and strengthen the stability and identifiability of causal discovery. Extensive experiments on HTTP Archive, Chrome UX Report (CrUX), and a synthetic ground truth dataset demonstrate that our framework achieves higher causal accuracy, more stable predictive performance, more effective intervention recommendations, and improved interpretability compared with existing rule-based, statistical, and machine learning baselines. These results highlight the potential of causality-aware analysis for practical web performance optimization. Full article

As prosthetic technologies become increasingly data-rich and embedded in care systems, traditional human-centred approaches often fall short of addressing evolving use realities. This paper contributes an applied computing framework that enables semantic reasoning and data-driven adaptation within prosthesis aftercare. We present an ontology-driven, cyber–physical prosthesis service system designed to enable personalised and adaptive care. Implemented through the Adaptive Prosthesis Life-Cycle Service System (adProLiSS) framework and demonstrated via a smart prosthesis prototype, the system treats the prosthesis as a semi-autonomous actor within an emotionally responsive and semantically mediated ecosystem. The proposed architecture integrates sensor data acquisition, ontology-based knowledge representation, and semantic reasoning to enable context-aware decision support and adaptive personalisation. A layered cyber–physical infrastructure, comprising embedded sensors, semantic reasoning, and user feedback through a digital twin interface, supports personalised aftercare, cross-disciplinary collaboration, and reflective design engagement. Evaluation with 26 participants across clinical, engineering, and user groups confirmed the system’s value in enhancing functionality, reducing downtime, and supporting emotional well-being. By positioning ontologies as both computational enablers and design support mechanisms, this research contributes a practical and scalable model for prosthetic service systems that adapt across bodily, emotional, and ecological dimensions, advancing more responsive and consequence-aware care practices. Full article

This paper presents an implemented methodology to convert highly detailed building information models (BIMs) into geospatial 3D city models (Geos) at multiple levels of detail (LoDs). As BIM models contain highly detailed and complex geometries that differ significantly from city model standards, abstraction and conversion methods are required to generate usable outputs. Our study addresses this by developing a methodology that generates nine different LoDs from a single IFC input. These LoDs include both volumetric and surface-based abstractions for exterior and interior representations. The methodology involves voxelisation, filtering and simplification of surfaces, footprint derivation, storey abstraction, and interior geometry extraction. Together, these approaches allow flexible conversion tailored to specific applications, balancing accuracy, complexity, and computational efficiency. The methodology is implemented in a prototype tool named IfcEnvelopeExtractor. It automates IFC-to-CityGML/CityJSON conversion with minimal user input. The methodology was tested on a variety of models ranging from small houses to multistorey buildings. The evaluation covered geometric accuracy, semantic accuracy, and model complexity. Results show that non-volumetric abstractions and interior abstractions performed very well, producing robust and accurate results. However, the accuracy decreased for volumetric and complex abstractions, particularly at higher LoDs. Problems included missing or incorrectly trimmed surfaces, and modelling gaps and tolerance issues in the input IFC models. These limitations reveal that the quality of the input BIM models significantly affects the reliability of conversions. Overall, the methodology demonstrates that automated, flexible, and open-source solutions can effectively bridge the gap between BIM and geospatial domains, contributing to scalable GeoBIM integration in practice. Full article

Event-based social network is a novel platform where users establish social relationships and realize interest matching through participation in offline events. However, event recommendation faces severe challenges, including extreme data sparsity due to the short life cycles of events, and the dynamic interplay between individual and group preferences on fine-grained features. Existing methods ignore the users’ diverse and personalized preferences across different event features such as venue and organizer. We first conduct a data analysis to argue that not only do users themselves have different preferences for different features, but more importantly, these preferences dynamically influence the behavior of different groups they belong to. Therefore, in this work, we propose a novel Multiple Attention Group Event Recommendation (MAGER) framework based on Neural Collaborative Filtering to address these challenges. MAGER first employs fine-grained feature attention to generate personalized event representations, and then dynamically aggregates member preferences and influences through a group-level attention mechanism. More importantly, a heterogeneous attention structure integrates these learning modules, enabling generation of more accurate representations of event, users, and groups. We conduct extensive experiments on three-real world datasets, the experimental results show that MAGER achieves substantial improvements in user and group recommendations effectiveness compared to baselines in terms of HR@K and NDCG@K. Specifically, HR@5 improvement of 3.63–13.07%; NDCG@K improvement of 5.63–18.55% for user recommendation, and HR@5 improvement of 2.05–19.02%; NDCG@K improvement of 2.51–36.12% for group recommendation on three datasets. Full article

Effective web service selection and recommendation are critical for ensuring high-quality performance in distributed and service-oriented systems. Recent research has increasingly explored the use of BERT (Bidirectional Encoder Representations from Transformers) to enhance semantic understanding of service descriptions, user requirements, and Quality of Service (QoS) prediction. This systematic review examines the application of BERT-based models in QoS-aware web service selection and recommendation. A structured database search was conducted across IEEE, ACM, ScienceDirect, and Google Scholar covering studies published between 2020 and 2024, resulting in twenty-five eligible articles based on predefined inclusion criteria and PRISMA screening. The review shows that BERT improves semantic representation and mitigates cold-start and sparsity issues, contributing to better service ranking and QoS prediction accuracy. However, challenges persist, including limited availability of benchmark datasets, high computational overhead, and limited interpretability of model decisions. The review identifies five key research gaps and outlines future directions, including domain-specific pre-training, hybrid semantic–numerical models, multi-modal QoS reasoning, and lightweight transformer architectures for deployment in dynamic and resource-constrained environments. These findings highlight the potential of BERT to support more intelligent, adaptive, and scalable web service management. Full article