Search Results (1,057)

Background/Objective: Autonomous vehicles (AVs) require control algorithms capable of handling complex and dynamic environments while satisfying multiple conflicting objectives such as safety, comfort, energy efficiency, and trajectory accuracy. Model predictive control (MPC) offers a principled framework for multi-constraint optimization, yet its real-time feasibility remains challenging for nonlinear vehicle dynamics. Methods: This paper presents a feedforward neural network (FNN)-based MPC framework for autonomous vehicle trajectory tracking. The FNN approximates the coupled vehicle dynamics and visual preview error model using an algebraic sum of log-sigmoid functions. Three adaptive FNN parameter sets, namely, the scaling factor, convergence parameter, and time-shifting parameter, are jointly optimized using a hybrid algorithm that combines the global search capability of fractional particle swarm optimization (FPSO) with the local refinement of sequential quadratic programming (SQP). Results: Comprehensive scenario-based simulations are performed to evaluate trajectory tracking dynamics under dry conditions with an adhesion coefficient of 0.8 and a vehicle mass of 1723 kg moving at a speed of 80 km/h. The results are quantitatively compared with a traditional PID controller and a structurally comparable MPC framework from the literature under identical simulation conditions; related DRL- and RL-based methods are discussed qualitatively for contextual orientation only. The stability, reliability, and computational complexity of the proposed framework are examined based on the mean square error, fitness value, and computational budget in GFLOPs for 100 independent runs. Conclusions: The proposed FNN-based MPC framework demonstrates improved tracking accuracy and optimizer reliability in simulation. While the present results indicate promising computational behavior, real-time deployment will require further validation on embedded automotive hardware and under closed-loop real-time constraints. Full article

In class-incremental learning (CIL), a model must learn new classes while retaining previous knowledge without storing all historical data. Generative replay mitigates catastrophic forgetting by synthesizing old class samples, but conventional pipelines usually train separate generative and classification models and can be degraded by generated images of poor quality. This paper proposes the Co-Diffusion Classifier (CoDC), a unified framework based on diffusion that performs image generation and classification in a single network. CoDC attaches a classification branch to the UNet encoder and introduces an exponential noise filtering loss according to diffusion timesteps so that cleaner samples contribute more strongly to representation learning. A base task classification pre-training stage followed by collaborative training with selective parameter freezing reduces conflicts between noise prediction and semantic feature extraction. For rehearsal-free replay, generated samples are selected using confidence and feature consistency filters. Experiments on CIFAR-100, FaceScrub, and Flowers-102 show that CoDC maintains strong incremental accuracy without storing real old class exemplars. Additional comparisons that account for protocol differences with recent exemplar-free and pre-trained model methods clarify the setting in which CoDC is most directly comparable. Full article

Mass concrete design presents a significant challenge due to the inherent conflicts among key performance metrics: high compressive strength, low heat of hydration, and low water absorption (a key durability indicator). Traditional trial-and-error methods are inefficient and fail to systematically navigate these complex trade-offs. To address this, this study proposes a data-driven multi-objective optimization framework for mass concrete mix design. A comprehensive experimental dataset of 64 mixtures was established by varying the water-to-binder ratio (0.40–0.55), fly ash content (0–120 kg/m³), and slag content (0–120 kg/m³), with cement content fixed at 400 kg/m³. Kriging surrogate models were developed to accurately map the nonlinear relationships between these design variables and the three performance responses. These models were then integrated with the NSGA-II algorithm to generate a Pareto-optimal front of solutions. The framework’s predictive accuracy and generalization capability were rigorously validated through out-of-sample experiments, demonstrating prediction errors consistently below 10%. The results provide a quantified map of feasible engineering compromises, enabling engineers to select tailored mixtures for specific project priorities, such as low-heat mixes for dams or high-strength mixes for foundations. Full article

Accurate viral protein function annotation is essential for genomic surveillance, yet conventional retrieval-augmented generation (RAG) pipelines often fragment biological evidence into fixed-length text chunks, disrupting relationships among ORFs, annotations, structural domains, sequence motifs, residue mappings, and model-derived attention evidence. We propose ViroBioTree, a tree-structured biological evidence retrieval framework for downstream viral protein evidence review rather than a new primary annotation classifier. Built as an evidence organization layer on ViralMultiNet-derived ORF-level predictions and annotations, ViroBioTree converts sequence, annotation, structure, and attention evidence into typed biological nodes and traceable edges, then performs deterministic multi-channel recall, evidence-aware reranking, balanced TopK selection, rule-based verification, and node-cited report generation. In a demo benchmark, ViroBioTree achieved its strongest deterministic proxy performance on structure-explanation tasks, with Precision@K = 1.0, Recall@K = 1.0, and diversity = 0.52; these values reflect expected node-type and tag agreement rather than independent biological correctness. A bounded full-scale SARS-CoV-2 index contained 39,800 ORF rows, 80,000 attention records, 199,418 nodes, and 495,886 edges. In a stratified full20k diagnostic evaluation, ViroBioTree showed task-dependent advantages over LlamaIndex vector retrieval for conflict detection, evidence retrieval, and structure explanation, while LlamaIndex remained competitive or stronger for annotation-rich function annotation. A cross-family Influenza A Virus (IAV) diagnostic audit showed that the schema can represent IAV evidence namespaces while explicitly exposing missing formal ORF inputs, missing attention evidence, and unavailable residue/PDB assertions. Supplementary robustness, external sanity-check, diversity-risk, expert-evaluation, domain-tool positioning, and cross-family audit analyses supported traceability, report quality, and conservative evidence handling, but also showed that stable Precision@K under query perturbation does not necessarily imply stable retrieved evidence sets. ViroBioTree operates offline and deterministically, but does not address raw-read assembly, base calling, primary ORF prediction, or wet-lab validation. Its results should be interpreted as proxy and expert-reviewed evidence for traceable viral protein evidence retrieval and report generation rather than as direct validation of biological function annotation. Full article

To address the performance degradation caused by coupling interference between control and identification filters in the active control of ship hydraulic systems, a multi-strategy collaborative optimization algorithm based on “Signal–Amplitude–Time” is proposed. The method constructs a variable-power white-noise module based on power factors to reduce auxiliary noise interference. It employs an improved variable-step-size LMS algorithm to achieve fast and high-precision online identification of the secondary path. Furthermore, an adaptive prediction error filter is introduced to decouple the control and identification processes, effectively resolving the conflict between convergence speed and steady-state precision. Simulation and experimental results demonstrate that the proposed optimization algorithm exhibits superior robustness and adaptive capability under various operating conditions. It can track complex load fluctuations in real time and achieve a line-spectrum pulsation attenuation of more than 90%. This multi-strategy collaborative scheme significantly enhances the pulsation suppression accuracy and dynamic response capability of ship hydraulic systems, providing an efficient and reliable technical approach for the acoustic stealth control of naval ship hydraulic systems. Full article

Sustainability monitoring has mainly focused on measuring where countries stand today, rather than anticipating where they are headed. This study develops an AI-based forecasting framework to predict national sustainability outcomes and identify countries whose actual paths deviate from predictions. Using 749 World Development Indicators across 184 countries and regions from 2003 to 2022, a Temporal Fusion Transformer (TFT) is developed using data from 2003 to 2017 (training and validation) and evaluated on a held-out 2018 to 2022 test period, with calibrated prediction intervals constructed retrospectively over the test period. Assuming that historical development patterns remain informative over the forecast horizon, the model achieves mean absolute errors of 1.10 for the Sustainable Development Goals Index (SDGI, 0 to 100 scale) and 0.008 for the Human Development Index (HDI, 0 to 1 scale), reducing error by at least 19 percent for SDGI and 60 percent for HDI relative to linear trend and XGBoost baselines. Of 184 countries and regions, 115 (62 percent) are classified as on-track for both indices. Among the rest, 35 show positive SDGI deviations, mostly developing nations in Sub-Saharan Africa and South Asia that are exceeding their forecast trajectories, while 23 show negative HDI deviations concentrated among nations affected by conflict and economic disruption. We find this asymmetric pattern is consistent with a decoupling between goal-level and capability-level sustainability, in which policy-driven SDG indicators can advance while foundational human development in health and income stalls. Our model identifies economic indicators as the dominant predictors of HDI (7 of the top 10), while SDGI prediction draws on a more balanced mix of economic, social, environmental, and institutional indicators. We also find that better governance is associated with lower prediction error for both SDGI (p = 0.004) and HDI (p < 0.001), suggesting that countries and regions with stronger institutions follow more predictable sustainability trajectories. Full article

Early identification of at-risk students is crucial for timely pedagogical intervention. Determining which assessments instructors should prioritize is complicated by the fact that different eXplainable-AI (XAI) methods can produce conflicting rankings for the same predictive model. We develop a framework combining a sequential GRU model with two complementary XAI techniques, Gradient SHAP (attribution) and DiCE (counterfactuals), and evaluate it in a foundational Data Structures and Algorithms course. The framework produces predictions and explanations for every prefix length throughout the semester and quantifies inter-method agreement and intra-method stability using three disagreement metrics. Intersecting the top-k features identified by both methods isolates a compact subset of assessments whose predictive role is confirmed across two fundamentally different explanation mechanisms. We interpret this cross-method agreement as a heuristic that increases confidence in identified features relative to single-method results, though not as evidence of causal validity. For individual students, the framework uses the intersection of the two types of explanations when it is non-empty; otherwise, the instructor chooses between SHAP’s diagnostic view and DiCE’s prescriptive view, with an optional check against the top-k list. The resulting guidance is less susceptible to method-specific biases than analyses relying on a single method. Full article

Existing deep learning methods for lithium-ion battery State of Health (SOH) prediction rely almost exclusively on discharge voltage–current curves, ignoring electrochemical impedance spectroscopy (EIS) data that directly reflects internal degradation mechanisms. Fusing these two modalities is non-trivial: discharge curves are high-dimensional temporal sequences residing on a continuous dynamical manifold, while impedance features are low-dimensional static snapshots with fundamentally different statistical distributions. However, naive concatenation introduces modal conflicts rather than complementary gains. We propose the Hybrid Sensing Synergy Architecture (HSSA), which combines a Mamba backbone ($O\left(L\right)$ complexity) for discharge curve modeling with a Q-former module that aligns impedance features into the temporal representation space via learnable query tokens and cross-attention. A prepend fusion strategy injects the aligned queries as prefix tokens, enabling the backbone to condition on internal electrochemical context from the first time step. On the NASA battery dataset, HSSA achieves MAE of 0.887 (large-scale, 11 batteries, a 9.8% improvement over unimodal Mamba), 1.457 (medium-scale, five batteries, a 28.0% improvement), and 2.705 (small-scale, four batteries, an 8.7% improvement), demonstrating consistent improvements across all data regimes. On out-of-sample battery B28, HSSA achieves 65.3% improvement. Ablation studies confirm that Q-former alignment is essential and prepend fusion significantly outperforms concatenation-based alternatives. Full article

Gas-phase sensors suffer from non-linear drift and range-precision conflicts, while the detection of dissolved H₂S in the oil phase relies on discontinuous, offline chemical analysis. To address these challenges, this study proposes a dual-output soft sensing model based on a Particle Swarm Optimization-Extreme Learning Machine (PSO-ELM). Unlike conventional single-output PSO-ELM applications, the proposed framework jointly performs gas-phase sensor drift correction and oil-phase dissolved H₂S estimation within a unified soft-sensing structure. By integrating gas sensor array signals with oil-phase process parameters, the model utilizes PSO to globally optimize the input weights and biases of the ELM, effectively overcoming the local minima and overfitting issues inherent in traditional neural networks. Field sampling results showed that the proposed model achieved high predictive accuracy, with coefficients of determination of 0.9949 for gas sensor drift correction and 0.9967 for oil-phase soft sensing. Comparative analysis reveals that the PSO-ELM significantly outperforms Standard ELM, RBF-ELM, and GA-ELM, reducing the Mean Squared Error by approximately 39.7% compared to GA-ELM. Furthermore, 5-fold cross-validation confirms the model’s robustness (R² average of 0.9810), indicating its potential for real-time hydrogen sulfide monitoring in complex oilfield production environments. Full article

Climate variability, environmental uncertainty, and carbon-market dynamics increasingly challenge agricultural investment and resource allocation decisions worldwide. This study proposes an integrated hybrid decision-support framework combining Long Short-Term Memory (LSTM) deep learning, Interval Type-2 Fuzzy Logic Systems, and Genetic Algorithms to support climate-resilient agricultural investment analysis under uncertainty. The framework integrates predictive modeling, uncertainty representation, and multi-objective optimization within a unified computational architecture. The empirical analysis was conducted using agricultural, climate, and carbon-market datasets covering Europe, Asia, and Africa over the 2010–2025 period. Agricultural productivity indicators, commodity price variables, climate-risk parameters, and carbon-market data were integrated into the modeling process. LSTM models were employed to analyze temporal agricultural and climate-related dynamics, while Interval Type-2 fuzzy systems were used to represent ambiguity associated with environmental and market uncertainty. Genetic Algorithms were subsequently applied to optimize investment allocation under conflicting objectives related to profitability, sustainability, and risk. The findings suggest that the proposed hybrid framework may improve adaptive investment evaluation and optimization performance under uncertain climate conditions relative to standalone computational approaches within the scope of the analyzed datasets. The results further highlight the importance of integrating predictive analytics, uncertainty modeling, and sustainability-oriented optimization within agricultural decision-support systems. However, the framework should be interpreted as a climate-resilient decision-support architecture rather than a universally deterministic forecasting mechanism. Overall, the study contributes to the emerging literature on agricultural sustainability and climate-resilient investment by presenting a transparent and uncertainty-aware computational framework under evolving environmental and carbon-market conditions. Full article

Background/Objectives: Parenting interventions are an effective way to support child development, and brief screening tools can support equitable implementation of parenting interventions by reducing program costs, increasing accessibility, and engaging populations who have traditionally been underserved. However, brief assessments are frequently overlooked and underutilized. The Family Check-Up (FCU) Online is a digital parenting intervention that integrates a brief FCU Online Assessment, feedback, and parenting skills via an app along with optional provider support. To date, no prior work has validated the FCU Online Assessment. Method: The current study combined two samples of parents participating in FCU Online studies and assessed: (1) reliability, (2) construct validity, (3) convergent validity by comparing FCU Online Assessment subscales to similar parenting and child behavior measures, and (4) predictive validity by using FCU Online Assessment at pretest to predict posttest scores as well as parenting and child behaviors at time 2 and time 3. Results: Strong reliability was found among all five subscales, including Low Conflict (7 items, α = .81), Positive Parenting Practices (11 items, α = .80), Positive School Behaviors (5 items, α = .83), Consistent Rules and Routines (11 items, α = .81), and Child Mental Health (5 items, α = .80). The FCU Online Assessment demonstrated construct and convergent validity, as well as predictive validity in that the FCU Online Assessment at pretest predicted posttest scores. Conclusions: The FCU Online Assessment is a brief, reliable, and valid measure of parenting and child wellbeing. It can be used by parents and providers alike to evaluate parenting skills and child mental health, develop targeted goals and intervention approaches, and assess family wellbeing over time. Full article

To address the conflict between real-time performance and global optimality in the energy management of dual-motor plug-in hybrid electric vehicles (PHEVs), this paper proposes a model predictive control (MPC) strategy based on dynamic programming (DP). Firstly, a radial basis function (RBF) neural network is employed to predict future driving conditions, providing preview information for the MPC. Subsequently, a DP-MPC cooperative architecture is constructed, which invokes DP to solve for local optimal solutions during the receding horizon optimization process and incorporates linear reference SOC trajectory planning to approximate the global optimum. Simulation results under the WLTC driving cycle demonstrate that the fuel consumption of the proposed strategy is 2.311 L/100 km, representing a 33.2% reduction in pure fuel consumption compared to the rule-based (RB) strategy, and a 16.3% reduction in equivalent fuel consumption (including electricity converted to fuel based on the engine’s generation efficiency), while achieving 96.31% of the fuel economy of the global optimal DP strategy. The study validates that this method significantly improves fuel economy while guaranteeing real-time performance. Full article

Designing ultra-high-performance concrete (UHPC) mixtures requires balancing multiple, often conflicting, performance criteria, particularly mechanical strength and rheological behavior. However, the limited availability of publicly accessible datasets containing synchronized multi-property measurements, together with cross-source heterogeneity, poses a major challenge for robust data-driven modeling under small-sample conditions. To address this issue, this study proposes an integrated framework combining cross-source data harmonization, Variational Autoencoder (VAE)-based latent-space augmentation, multi-output deep learning, interpretability analysis, and Genetic Algorithm (GA)-driven inverse design. A dataset comprising 139 valid UHPC records was curated from 22 peer-reviewed studies and expanded to 2780 samples through VAE-based augmentation. Using the augmented dataset, a multi-output deep neural network was developed to jointly predict compressive strength, flexural strength, yield stress, and plastic viscosity. On the independent test set, the model achieved R² values of 0.8601, 0.9212, 0.8464, and 0.6603, respectively. Comparative benchmarks and augmentation ablation analyses further showed that VAE-based augmentation consistently improved predictive performance and generalization, especially under small-sample conditions. SHAP and partial dependence analyses identified curing age, steel fiber content, water-to-binder ratio, and superplasticizer dosage as the dominant factors governing UHPC performance. Finally, the trained surrogate model was coupled with a GA for multi-objective inverse optimization, and experimental validation of three candidate mixtures confirmed good agreement between predicted and measured values. This study provides a transparent and engineering-oriented methodology for the integrated prediction, interpretation, and optimization of UHPC mixtures. Full article

The structural integrity and risk management of long-distance oil and gas pipelines are critically challenged by multi-source data heterogeneity, complex multi-physics degradation mechanisms, and the dynamic nature of operational environments. Traditional monolithic artificial intelligence models struggle with cross-domain knowledge fusion and often suffer from historical context forgetting over decades-long infrastructure lifecycles. To address these bottlenecks, this paper proposes an evolutionary digital twin framework driven by a collaborative architecture between small specialized models and a large general model. Specifically, the framework encapsulates physics-informed models (e.g., corrosion prediction and geohazard evaluation) as domain expert agents to guarantee rigorous numerical computation at the edge, keeping sensitive operational data strictly localized. To synthesize conflicting localized risks, a locally deployed, privacy-preserving large language model acts as a central cognitive hub. This hub utilizes external knowledge retrieval and structured reasoning to formulate transparent, multi-objective intervention strategies. Furthermore, a continuous feedback learning mechanism is introduced to capture tacit expert knowledge. By formalizing human operational interventions into historical memory and employing parameter stabilization techniques, the system dynamically updates its knowledge base while effectively mitigating catastrophic forgetting. Ultimately, the proposed framework provides a reliable and privacy-compliant methodology, significantly enhancing the interpretability and predictive foresight of pipeline integrity management. Full article

Although heritage reconstruction can effectively restore physical form, the regeneration of living cultural experience remains theoretically underexplored in heritage tourism scholarship. This study introduces the concept of post-reconstruction experiential disjunction (PRED)—the structural misalignment among reconstructed material form, historically embedded cultural scripts, and the embodied practices of contemporary visitors—and develops the Material–Script–Practice (MSP) framework around it. Taking Yuyuan Garden (愚园) in Nanjing as an empirical case, a mixed-methods design combines online discourse analysis, field observation, and a questionnaire survey (N = 300). Findings reveal that Cultural Script most strongly predicts disjunction mitigation—a four-item scale capturing visitors’ holistic sense of experiential connectivity (α = 0.832), followed by Material Form; Embodied Practice contributes comparatively little. Photographers show significantly lower mitigation levels than other groups, owing to structural conflicts between professional visual practice and the cultural logic of classical garden space. The MSP framework reveals a weighted hierarchy among its three dimensions: a finding that extends and empirically specifies the theoretical insights of Lefebvre’s spatial triad and Edensor’s heritage performance theory, neither of which typically foregrounds differential explanatory weight among their constituent elements. When cultural scripts offer accessible meaning pathways for visitors of diverse backgrounds, heritage spaces can move beyond formal reconstruction toward experiential reconstitution, sustaining the conditions for long-term heritage preservation. Full article