Search Results (3,871)

Diesel engines serve as critical power sources across transportation and industrial fields, and their fault diagnosis is essential for ensuring operational safety and system reliability. However, acquiring sufficient and effective operational data remains a significant challenge due to the high complexity of the systems. As a modeling method that incorporates expert knowledge, the belief rule base (BRB) demonstrates strong potential in resolving such challenges. Nevertheless, the reliance on expert knowledge constrains its practical application, particularly in complex engineering scenarios. To overcome this limitation, this study proposes a reliability fault diagnosis method for diesel engines based on the belief rule base with data-driven initialization (DI-BRB-R), which aims to improve modeling capability under conditions of limited expert knowledge. Specifically, the approach first employs fuzzy c-means clustering with the Davies–Bouldin index (DBI-FCM) to initialize attribute reference values. Then, a Gaussian membership function with Laplace smoothing (LS-GMF) is developed to initialize the rule belief degrees. Furthermore, to guarantee the reliability of the model optimization process, a group of reliability guidelines is introduced. Finally, the effectiveness of the proposed method is validated through an example of fault diagnosis of the WD615 diesel engine. Full article

Urban tree planting on single-family-home lots represents a critical yet underexplored component of municipal greening strategies. This study examines residents’ perceptions of tree planting in Westpointe, a diverse neighborhood in Salt Lake City, Utah, as part of the city’s Reimagine Nature Public Lands Master Plan development effort. Through a mixed-methods approach combining qualitative interviews (n = 24) and a tree signup initiative extended to 86 residents, with 51 participating, this research explores the complex interplay of demographic, economic, social, and infrastructure factors influencing residents’ willingness to plant trees on single-family-home lots. The findings reveal significant variations based on gender, with women expressing more positive environmental and aesthetic motivations, while men focused on practical concerns including maintenance and property damage. Age emerged as another critical factor, with older adults (65+) expressing concerns about long-term maintenance capabilities, while younger families (25–44) demonstrated future-oriented thinking about shade and property values. Property characteristics, particularly yard size, significantly influenced receptiveness, with owners of larger yards (>5000 sq ft) showing greater willingness compared to those with smaller properties, who cited space constraints. Additional barriers, i.e., maintenance, financial, and knowledge barriers, included irrigation costs, lack of horticultural knowledge, pest concerns, and proximity to underground utilities. Geographic analysis revealed that Spanish-speaking social networks were particularly effective in promoting tree planting. The study contributes to urban forestry literature by providing nuanced insights into single-family homeowners’ tree-planting decisions and offers targeted recommendations for municipal programs. These include gender-specific outreach strategies, age-appropriate support services, sliding-scale subsidy programs based on property size, and comprehensive education initiatives. The findings inform evidence-based approaches to increase urban canopy coverage through private property plantings, ultimately supporting climate resilience and environmental justice goals in diverse urban neighborhoods. Full article

Predictive maintenance (PdM) is vital to maritime operations; however, the traditional deep learning solutions currently offered heavily depend on centralized data aggregation, which is impractical under the limited connectivity, privacy concerns, and resource constraints found in maritime vessels. Federated Learning addresses privacy by training models locally, yet most FL methods assume homogeneous client architectures and exchange full model weights, leading to heavy communication overhead and sensitivity to system heterogeneity. To overcome these challenges, we introduce FLUID, a dynamic, model-agnostic FL framework that combines client clustering, structured pruning, and student–teacher knowledge distillation. FLUID first groups vessels into resource tiers and calibrates pruning strategies on the most capable client to determine optimal sparsity levels. In subsequent FL rounds, clients exchange logits over a small reference set, decoupling global aggregation from specific model architectures. We evaluate FLUID on a real-world heavy-fuel-oil purifier dataset under realistic heterogeneous deployment. With mixed pruning across clients, FLUID achieves a global $R^2$ of 0.9352, compared with 0.9757 for a centralized baseline. Predictive consistency also remains high for client-based data, with a mean per-client MAE of 0.02575 ± 0.0021 and a mean RMSE of 0.0419 ± 0.0036. These results demonstrate FLUID’s ability to deliver accurate, efficient, and privacy-preserving PdM in heterogeneous maritime fleets. Full article

Middle leaders are acknowledged as important leaders within schools to support and improve teaching and learning. While middle leaders’ (MLs) knowledge and skills are foundational for contributing to school improvement, social emotional intelligence (SEI) has been identified as a crucial capability for developing and maintaining trusting relationships and collaborative teams, both of which are essential for leading school improvement, a central focus of ML work. To understand the empirical evidence base on MLs and SEI, a scoping literature review was conducted. Although empirical research was limited, SEI consistently emerged as a critical factor influencing a range of middle leadership (ML) outcomes. To extend the review findings, a problem-centered interview approach was undertaken with five MLs. The interviews sought to identify the SEI competencies perceived as supportive of ML practices and positive outcomes for both MLs and colleagues. Insights from the literature review and interviews converged to highlight empathy and emotional self-management as foundational SEI competencies. Both competencies were found to underpin several key leadership outcomes, including the regulation of emotions, both personal and interpersonal, for the development of collegial relationships, and the enhancement of ML wellbeing. Considering these findings, professional learning (PL) to foster ML SEI competencies is presented. Full article

The purpose of the current research study was to identify appropriate educators for teaching entrepreneurship at the university level and to explore the best teaching methods for developing entrepreneurial knowledge and skills among students. The study aims to address two key questions in entrepreneurship education: (1) Who should teach entrepreneurship in universities? and (2) What methods are effective in teaching entrepreneurship in universities? The study was conducted using an interpretative phenomenological qualitative research approach. Data were collected from a purposive sample of eight (8) entrepreneurship educators from a South African university. Data collection spanned three months, from November 2024 to January 2025. The key findings of the study suggest that entrepreneurship should be taught by academics with practical experience, academics with at least a Master’s degree, entrepreneurs invited as guest lecturers, incubator professionals, and technology professionals. Additionally, the research revealed teaching methods that can be used to effectively teach entrepreneurship in universities: Universities need to prioritise hiring and training entrepreneurship educators with both academic and real-world experience and facilitate collaborations with incubators and real-world entrepreneurs. Teaching methods need to incorporate experiential learning methods such as startup simulations, case studies, and partnerships with innovation hubs. The study offers valuable insights into who should teach entrepreneurship and how it should be taught, emphasising the need for a multidisciplinary approach and practical orientation to develop entrepreneurial capabilities and mindsets among students. Full article

Scene Knowledge-guided Visual Grounding (SK-VG) is a multi-modal detection task built upon conventional visual grounding (VG) for human–computer interaction scenarios. It utilizes an additional passage of scene knowledge apart from the image and context-dependent textual query for referred object localization. Due to the inherent difficulty in directly establishing correlations between the given query and the image without leveraging scene knowledge, this task imposes significant demands on a multi-step knowledge reasoning process to achieve accurate grounding. Off-the-shelf VG models underperform under such a setting due to the requirement of detailed description in the query and a lack of knowledge inference based on implicit narratives of the visual scene. Recent Vision–Language Models (VLMs) exhibit improved cross-modal reasoning capabilities. However, their monolithic architectures, particularly in lightweight implementations, struggle to maintain coherent reasoning chains across sequential logical deductions, leading to error accumulation in knowledge integration and object localization. To address the above-mentioned challenges, we propose SplitGround—a collaborative framework that strategically decomposes complex reasoning processes by fusing the input query and image with knowledge through two auxiliary modules. Specifically, it implements an Agentic Annotation Workflow (AAW) for explicit image annotation and a Synonymous Conversion Mechanism (SCM) for semantic query transformation. This hierarchical decomposition enables VLMs to focus on essential reasoning steps while offloading auxiliary cognitive tasks to specialized modules, effectively splitting long reasoning chains into manageable subtasks with reduced complexity. Comprehensive evaluations on the SK-VG benchmark demonstrate the significant advancements of our method. Remarkably, SplitGround attains an accuracy improvement of 15.71% on the hard split of the test set over the previous training-required SOTA, using only a compact VLM backbone without fine-tuning, which provides new insights for knowledge-intensive visual grounding tasks. Full article

Under the framework of the “dual-carbon” goals of China (“carbon peak” by 2030 and “carbon neutrality” by 2060), the escalating complexity of emerging power systems presents significant challenges to safety governance. Traditional management models are now confronting bottlenecks, notably in knowledge inheritance breakdown and lagging risk prevention and control. This paper explores the application of large AI models in safety and emergency management in the power industry. Through core capabilities—such as natural language processing (NLP), knowledge reasoning, multimodal interaction, and auxiliary decision making—it achieves full-process optimization from data fusion to intelligent decision making. The study, anchored by 18 cases across five core scenarios, identifies three-dimensional challenges (including “soft”—dimension computing power, algorithm, and data bottlenecks; “hard”—dimension inspection equipment and wearable device constraints; and “risk”—dimension responsibility ambiguity, data bias accumulation, and model “hallucination” risks). It further outlines future directions for large-AI-model application innovation in power industry safety and management from a four-pronged outlook, covering technology, computing power, management, and macro-level perspectives. This work aims to provide theoretical and practical guidance for the industry’s shift from “passive response” to “intelligent proactive prevention”, leveraging quantified scenario-case analysis. Full article

Biodegradable polyesters have gained attention due to their sustainability benefits, considering the escalating environmental challenges posed by synthetic polymers. Advances in artificial intelligence (AI), including machine learning (ML) and deep learning (DL), are expected to significantly accelerate research in polymer science. This review article explores “bio” polymer informatics by harnessing insights from the AI techniques used to predict structure–property relationships and to optimize the synthesis of bioplastics. This review also discusses PolyID, a machine learning-based tool that employs message-passing graph neural networks to provide a framework capable of accelerating the discovery of bioplastics. An extensive literature review is conducted on explainable AI (XAI) and generative AI techniques, as well as on benchmarking data repositories in polymer science. The current state-of-the art in ML methods for ring-opening polymerizations and the synthesizability of biodegradable polyesters is also presented. This review offers an in-depth insight and comprehensive knowledge of current AI-based models for polymerizations, molecular descriptors, structure–property relationships, predictive modeling, and open-source benchmarked datasets for sustainable polymers. This study serves as a reference and provides critical insights into the capabilities of AI for the accelerated design and discovery of green polymers aimed at achieving a sustainable future. Full article

We present Liquid Adaptive AI as a theoretical framework and mathematical basis for artificial intelligence systems capable of continuous structural adaptation and autonomous capability development. This work explores the conceptual boundaries of adaptive AI by formalizing three interconnected mechanisms: (1) entropy-guided hyperdimensional knowledge graphs that could autonomously restructure based on information-theoretic criteria; (2) a self-development engine using hierarchical Bayesian optimization for runtime architecture modification; and (3) a federated multi-agent framework with emergent specialization through distributed reinforcement learning. We address fundamental limitations in current AI systems through mathematically formalized processes of dynamic parameter adjustment, structural self-modification, and cross-domain knowledge synthesis, while immediate implementation faces substantial computational challenges requiring infrastructure on the scale of current large language model training facilities, we provide architectural specifications, theoretical convergence bounds, and evaluation criteria as a foundation for future research. This theoretical exploration establishes mathematical foundations for a potential new paradigm in artificial intelligence that would transition from episodic training to persistent autonomous development, offering a long-term research direction for the field. A comprehensive ^{Supplementary Materials} document provides detailed technical analysis, computational requirements, and an incremental development roadmap spanning approximately a decade. Full article

Ultrasound imaging is widely used in early pregnancy to screen for fetal brain anomalies. However, the accuracy of diagnosis can be influenced by various factors, including the sonographer’s experience and environmental conditions. To address these limitations, advanced methods are needed to enhance the efficiency and reliability of fetal anomaly screening. In this study, we propose a novel approach based on a Fetal Brain Structures Detection Network (FBStrNet) for identifying key anatomical structures in fetal brain ultrasound images. Specifically, FBStrNet builds on the YOLOv5 baseline model, incorporating a lightweight backbone to reduce model parameters, replacing the loss function, and utilizing a decoupled detection header to improve accuracy. Additionally, our method integrates prior clinical knowledge to minimize false detection rates. Experimental results demonstrate that FBStrNet outperforms state-of-the-art methods, achieving real-time detection of fetal brain anatomical structures with an inference time of just 11.5 ms. This capability enables sonographers to efficiently visualize critical anatomical features, thereby improving diagnostic precision and streamlining clinical workflows. Full article

Although SAR systems can provide high-resolution aerial view images all-day, all-weather, the aspect and pose-sensitivity of the SAR target signatures, which defies the Gestalt perceptual principles, sets a frustrating performance upper bound for SAR Automatic Target Recognition (ATR). Therefore, we propose a network to support context-guided ATR by using aligned Electro-Optical (EO)-SAR image pairs. To realize EO-SAR image scene grammar alignment, the stable context features highly correlated to the parking patterns of the vehicle and aircraft targets are extracted from the EO images as prior knowledge, which is used to assist SAR-ATR. The proposed network consists of a Scene Recognition Module (SRM) and an instance-level Cross-modality ATR Module (CATRM). The SRM is based on a novel light-condition-driven adaptive EO-SAR decision weighting scheme, and the Outlier Exposure (OE) approach is employed for SRM training to realize Out-of-Distribution (OOD) scene detection. Once the scene depicted in the cut of interest is identified with the SRM, the image cut is sent to the CATRM for ATR. Considering that the EO-SAR images acquired from diverse observation angles often feature unbalanced quality, a novel class-incremental learning method based on the Context-Guided Re-Identification (ReID)-based Key-view (CGRID-Key) exemplar selection strategy is devised so that the network is capable of continuous learning in the open-world deployment environment. Vehicle ATR experimental results based on the UNICORN dataset, which consists of 360-degree EO-SAR images of an army base, show that the CGRID-Key exemplar strategy offers a classification accuracy 29.3% higher than the baseline model for the incremental vehicle category, SUV. Moreover, aircraft ATR experimental results based on the aligned EO-SAR images collected over several representative airports and the Arizona aircraft boneyard show that the proposed network achieves an F1 score of 0.987, which is 9% higher than YOLOv8. Full article

Against the background of carbon emission reduction, this paper explores the driving factors of carbon footprint knowledge system toughness for building construction enterprises through the theory of constraints (TOC) and optimises the carbon footprint knowledge system toughness under static and dynamic perspectives, respectively. Under the static perspective, the fuzzy set qualitative comparative analysis method (fsQCA) is used to explore the development path of the carbon footprint knowledge system toughness for building construction enterprises, and the study finds three kinds of grouping paths. Under the dynamic perspective, system dynamics is used to analyse the causality of the driving factors of the carbon footprint knowledge system toughness and draw the causality diagram. The stock flow diagram is drawn according to the relationship between the factors, and G1 method is combined with the expert distribution to determine the weight of each factor, and then, the model equation is established to complete the construction of the system dynamics of the carbon footprint knowledge system toughness based on the control variable method of the four capabilities under the influence of the factors to simulate the comparison and to explore the extent of the influence of different factors on the carbon footprint knowledge system toughness. Through the two-dimensional analysis framework, we provide an integrated solution for path selection and dynamic regulation for building construction enterprises to help them achieve the adaptive optimisation of the carbon footprint knowledge system and promote the low-carbon transformation and sustainable development of the construction industry. Qualitative results show that three configuration paths affect resilience, with core factors including management, emission, predictive, and construction capabilities. Quantitative results indicate fsQCA overall consistency (0.861) and coverage (0.808); system dynamics simulation shows that management capability has the highest impact weight (0.355). Full article

On food delivery platforms, user decisions are often driven by dynamic contextual factors such as time, intent, and lifestyle patterns. Traditional context-aware recommender systems struggle to capture such implicit signals, especially when user behavior spans heterogeneous long- and short-term patterns. To address this, we propose a context-driven recommendation framework that integrates a hybrid sequence modeling architecture with a Large Language Model for post hoc reasoning and reranking. Specifically, the solution tackles several key issues: (1) integration of multimodal features to achieve explicit context fusion through a hybrid fusion strategy; (2) introduction of a context capture layer and a context propagation layer to enable effective encoding of implicit contextual states hidden in the heterogeneous long and short term; (3) cross attention mechanisms to facilitate context retrospection, which allows implicit contexts to be uncovered; and (4) leveraging the reasoning capabilities of DeepSeek-R1 as a post-processing step to perform open knowledge-enhanced reranking. Extensive experiments on a real-world dataset show that our approach significantly outperforms strong baselines in both prediction accuracy and Top-K recommendation quality. Case studies further demonstrate the model’s ability to uncover nuanced, implicit contextual cues—such as family roles and holiday-specific behaviors—making it particularly effective for personalized, dynamic recommendations in high-frequency scenes. Full article

Extrapyramidal symptoms encompass features of Parkinsonism, including bradykinesia, cogwheel rigidity, and resting tremors, which contribute to motor impairments hindering handwriting and speech. In this study, we analyzed voice data captured using a voice sensor setup from 94 patients exhibiting varying levels of EPS and 30 unaffected controls. Each participant provided 13 recordings of repeated vowel and consonant sounds. The Drug-Induced Extrapyramidal Side Effect Scale and Glasgow Antipsychotic Side Effect Scales were used when grading patients into mild, moderate, and severe extrapyramidal symptoms, both administered by trained clinicians. To develop an objective assessment tool, we employed a transfer learning approach using a DenseNet architecture for feature extraction and classification. Its architecture enables the hierarchical concatenation of features at each layer. In this study, we identified that key acoustic features, MFCC, chroma, and spectral contrast vary significantly with the severity of extrapyramidal symptoms. Based on these findings, we developed a DenseNet-based model capable of predicting extrapyramidal symptoms from voice data. This model can classify with an accuracy of 81.9% and a precision of 82.0%. To the best of our knowledge, this is the first study to introduce a voice-based model for assessing the severity of extrapyramidal symptoms. Full article

Agentic AI and Large Language Models (LLMs) are transforming how language is understood and generated while reshaping decision-making, automation, and research practices. LLMs provide underlying reasoning capabilities, and Agentic AI systems use them to perform tasks through interactions with external tools, services, and Application Programming Interfaces (APIs). Based on a structured scoping review and thematic analysis, this study identifies that core challenges of LLMs, relating to security, privacy and trust, misinformation, misuse and bias, energy consumption, transparency and explainability, and value alignment, can propagate into Agentic AI. Beyond these inherited concerns, Agentic AI introduces new challenges, including context management, security, privacy and trust, goal misalignment, opaque decision-making, limited human oversight, multi-agent coordination, ethical and legal accountability, and long-term safety. We analyse the applications of Agentic AI powered by LLMs across six domains: education, healthcare, cybersecurity, autonomous vehicles, e-commerce, and customer service, to reveal their real-world impact. Furthermore, we demonstrate some LLM limitations using DeepSeek-R1 and GPT-4o. To the best of our knowledge, this is the first comprehensive study to integrate the challenges and applications of LLMs and Agentic AI within a single forward-looking research landscape that promotes interdisciplinary research and responsible advancement of this emerging field. Full article