Search Results (306)

This paper proposes AutoRL, a high-fidelity Robot Operating System 2 (ROS2)–Gazebo simulation pipeline that addresses a critical reproducibility gap in learning-based flight control: existing reinforcement learning (RL) frameworks for unmanned aerial vehicles (UAVs) lack deterministic, step-level coupling between control actions and physics updates. AutoRL enforces a strict one-to-one correspondence between agent actions and physics updates via blocking ROS2 service calls, preserving the Markov property required for stable policy learning and enabling verifiable reproducibility independent of the learning algorithm. A composite reward function jointly optimizes attitude tracking accuracy, oscillation suppression, actuator smoothness, and disturbance robustness. Its modular, service-oriented architecture provides a reusable framework for offline-trained RL research. A proximal policy optimization (PPO) controller trained within AutoRL validates the framework, demonstrating consistent convergence and stable performance across multiple independently seeded runs. Determinism was experimentally verified across two regimes: with Gaussian IMU noise disabled, repeated rollouts produced bit-identical trajectories, while with noise enabled, the measured distribution of trajectory divergence agreed with a reference distribution drawn from the declared sensor model, together confirming that the blocking service call architecture eliminates all non-stochastic sources of nondeterminism between the agent and the physics engine. The trained model is exported in a lightweight form compatible with embedded flight control firmware and remains adaptable across airframe configurations by automatically recomputing the control allocation matrix from configuration files. The total policy network contains only $\mathrm{10,628}$ trainable parameters, and inference was measured on a Cortex-M7 microcontroller at $598.7$ µs per step, $15.0\%$ of the 4 ms control period. Full article

Solomonoff induction mixes all computable explanations with description-length weights, but it is incomputable. This theory-and-position paper argues that practical approximation must be category-native: one should first declare the mathematical category in which a computable shadow will live, then use that category’s native comparison functional, complexity code, and inductive object. The proposal is not an omnibus theorem asserting that all categories are equivalent. It is a research architecture that separates comparison, representation, and prediction and makes the information lost by each projection explicit. The metric–measure branch supplies the developed realization. Compression data define an empirical Solomonoff space; Gromov–Wasserstein (GW) distance supplies relational distortion; minimum description length (MDL) controls candidate complexity; and distance-to-kernel embedding produces a positive-semidefinite predictor. For finite or countable coded classes, we prove existence and stability results, a held-out validation oracle inequality, a Kolmogorov–Solomonoff kernel unification, conditional empirical-GW consistency, and a coding-redundancy bound. Stronger learning-oracle statements remain conditional on marked/predictive selection, candidate-family adequacy, and kernel stability. Topological, Banach/Barron, graph, tree, and operator branches are presented as a constructional and testable research programme, with their maturity stated explicitly. Full article

This paper investigates the relationship between the benefits achieved by predictive maintenance implementation and the related costs incurred intentionally or not. Specifically, we seek to establish an evaluation method for predictive maintenance that includes prediction model performance, which will better indicate that a predictive maintenance strategy built on the model will succeed in providing benefits compared to a pre-existing maintenance strategy. This will help justifying the costs and complexities of implementing new maintenance procedures and ensure positive financial outcomes. We demonstrate this method with a case study based on scheduled maintenance of an offshore wind farm where a declarative modeling approach is used to simulate service costs and operations, while a deep learning model provides insights on imminent downtime events. The results of this case study show that predictive maintenance is only profitable under specific conditions, such as limited service resources and high prediction model performance, and a profitable performance threshold for the underlying model is obtained. Full article

Switching-aware spectrum selection requires balancing interference avoidance against retuning costs. This paper evaluates a hybrid neural–polynomial deep Q-network (HNP-DQN) in an eight-channel, measurement-driven 5 GHz testbed with exogenous sweeping and random interference. The architecture combines learned latent features with an element-wise second-order expansion, layer normalization (LayerNorm), and a dueling Double Deep Q-Network (DDQN) backbone. Files are separated before window construction, and the evaluation includes a pre-inspected pilot and two outcome-uninspected distance and power transfers. The comparison includes strong deterministic rules and a capacity-matched multilayer perceptron (MLP) trained with the same DDQN procedure. All methods are evaluated on common trajectories with paired inference across 10 independently trained seeds and Holm correction. Under deterministic sweeping, the schedule-aware rule was given the declared initial phase and one-channel-per-step direction and used an internal step counter to track the deterministic progression. These schedule variables and the corresponding step index are absent from HNP-DQN’s 48-dimensional observation. The rule matched the trajectory-wise dynamic-programming upper bound and outperformed HNP-DQN in all three settings (differences calculated as HNP-DQN minus the rule: $-1.91$, $-3.51$, and $-1.97$; all adjusted $p=0.023$). This information-asymmetric operational comparison shows the advantage attainable when the declared sweep specification and its progression are directly exploited; however, it does not provide a matched-information architectural ranking. By contrast, under random jamming, all comparisons between HNP-DQN and the threshold rule were inconclusive after correction, as were all six capacity-matched comparisons between HNP-DQN and the MLP. Of the 24 exploratory ablation comparisons, one favored the $\gamma =0$ variant in the random pilot, whereas the other 23 were inconclusive. Accordingly, this paper provides an information-aware, approximately parameter-matched reference for evaluating when explicit knowledge, observation-based control, or additional learning complexity is justified within the declared measurement-replay scope. Full article

Machine learning (ML) models for alkali-activated concrete (AAC) are almost universally evaluated with random train–test splits, yet the literature-compiled datasets are strongly clustered by source study, and the reliability of such evaluations has rarely been quantified. The novelty of this study is a systematic quantification of out-of-campaign generalisation—via Leave-One-Study-Out (LOSO) cross-validation—for ML models trained on the largest curated public AAC dataset (1630 mixtures compiled from 106 published sources), together with model interpretation and an exploratory strength–carbon analysis. Four models (Linear Regression, Random Forest, Gradient Boosting, and optimised extreme gradient boosting, XGBoost) were benchmarked for predicting 28-day compressive strength (CS₂₈). XGBoost performed best under conventional random splitting, with test-set coefficient of determination R² = 0.801 and root-mean-square error (RMSE) = 7.21 MPa (5-fold cross-validation R² = 0.758 ± 0.050). Under LOSO validation across 85 study folds, however, the median R² collapsed to −0.328, with 49 of 85 folds negative: random-split metrics on literature-compiled AAC datasets are substantially inflated by within-study clustering, and study-stratified evaluation should become standard practice in this field. Within these limits, SHapley Additive exPlanations (SHAP) identified ground granulated blast-furnace slag (GGBFS) content, specimen geometry, CaO fraction, curing time, and sodium silicate (Na₂SiO₃) content as the five most influential predictors; because the oxide descriptors are derived from the declared binder proportions and the carbon-footprint values are inherited estimates from the source dataset, these attributions are associational rather than causal. No practically meaningful overall linear association was observed between estimated CO₂ footprint and CS₂₈ (Pearson r = −0.113, 95% CI [−0.175, −0.050], R² = 0.013), and a Pareto analysis identified 14 candidate low-carbon, high-strength formulations for further experimental and life-cycle assessment. The developed models are suitable for within-dataset feature attribution and exploratory screening restricted to the represented feature domain; they should not be used as external mix-design tools without validation on independent experimental campaigns. Full article

Claims of AI sovereignty are increasingly invoked but operational control remains uneven. Claims to control are made through national models, sovereign clouds, data localization mandates, and procurement rules; however, whether such claims translate into demonstrable control over how AI systems are run, inspected, and contested remains poorly understood. This paper introduces credible sovereignty, the gap between declared and demonstrable control in deployment, as a conceptual lens for analyzing AI governance to examine how this gap is opened and closed across infrastructure, data, and model supply chains. Using a PRISMA-guided social-science corpus and machine learning-based BERTopic modeling, validated through topic diversity and topic separation diagnostics and triangulated through close reading, the analysis identifies four governance logics through which sovereignty is contested: data infrastructure and legitimacy frameworks; techno-bloc diplomacy and infrastructure politics; European regulatory sovereignty; and community-driven sovereignty in the Global South. Across these logics, sovereignty is enacted less through national capabilities than through proxy mechanisms—certification regimes, procurement clauses, cloud governance, and deployment architectures—each carrying trade-offs between autonomy, dependence, and accountability. Rereading the corpus through an Antecedents–Decisions–Outcomes lens yields a testable research agenda: antecedents that push actors toward sovereignty seeking; design and governance choices that translate ambition into implementation; and outcomes—resilience, inclusion, accountability—against which sovereign AI programs should be assessed. This paper reframes sovereignty as a layered operational capability rather than a discursive claim and links computational synthesis to a normative construct that applies across jurisdictions and scales. Full article

Financial reporting oversight evolves through repeated feedback among managerial incentives, audit detection, board oversight, regulatory intervention, and market trust. I develop a transparent recursive simulation model to examine whether specified mechanism combinations can generate distinguishable governance trajectories within its rules. Monte Carlo simulations compare institutional scenarios, supported by analyses of uncertainty, alternative model designs, heterogeneous conditions, and a learning-agent extension. Within the simulations, high-transparency coordination generally produces the strongest governance outcomes, whereas weak governance remains consistently least favorable across the uncertainty analyses. In the model, governance improvement depends on interactions among disclosure, audit, regulation, and market feedback. In the learning-agent extension, learned policies yield less favorable governance and reporting outcomes than the fixed-policy benchmark. Chinese A-share evidence is broadly consistent with the main simulated patterns in direction, risk location, and broad ordering. These findings provide mechanism-sufficiency evidence within the declared rule family and explain how oversight signals become institutional outcomes and subsequent feedback. Full article

Relational databases power high-stakes decisions in lending, healthcare, and justice, yet SQL lacks native constructs for causal and counterfactual reasoning. Prior SQL-based causal systems address parts of this gap but do not unify treatment-effect estimation with counterfactual generation in a single, composable SQL surface. We present a system that extends the SQL dialect with two declarative operators: EXPLAIN_CAUSALLY_WHY ($\psi$) for estimating average and conditional treatment effects via meta-learners, and EXPLAIN_COUNTERFACTUAL ($\phi$) for generating diverse, constraint-respecting alternatives via a hybrid KD-tree/LSH pipeline. Both operators consume standard SQL relations (joins, filters, projections) and return table-valued results with optional diagnostics, confidence intervals, and feasibility metrics. We formalize the operators in relational algebra, and describe our prototype system called PsiQL. On four evaluation datasets, PsiQL recovers a protective TWINS treatment effect, returns a non-significant COMPAS point ATE with imbalance diagnostics, flags HMDA covariate imbalance via built-in SMD checks, and generates constraint-respecting counterfactuals; a synthetic Census run serves as a balanced pipeline proof-of-concept alongside a real ACS diagnostic under severe imbalance. Full article

This article analyzes the explicit and implicit presence of social justice in the graduation profiles of Social Work programs at Chilean state universities, as well as the way in which its distributive, recognition, and participatory dimensions are articulated within the declarative curriculum. An exploratory qualitative design was developed based on a comparative documentary analysis of twelve official graduation profiles, retrieved from institutional sources and analyzed through a matrix grounded in a plural conception of social justice. The results show that explicit references to social justice are exceptional and that, more frequently, it is expressed indirectly through references to human rights, public policies, diversity, human development, citizenship, or territory. The distributive dimension shows the greatest operational development, especially through public policies, program management, state action, social equality, and intervention in vulnerable contexts. The recognition dimension appears mainly at a declarative level, linked to diversity, pluralism, interculturality, and gender. The participatory dimension is the least operationalized, with limited references to deliberation, democratic governance, or shared decision-making. The study identifies three profile typologies: distributive-institutional; rights-, diversity-, and recognition-oriented; and relatively integrated profiles of plural social justice. The findings suggest that strengthening curricular coherence may require moving from general normative statements toward competencies, learning outcomes, and assessment criteria capable of integrating redistribution, recognition, and participation in professional education. Full article

Background: Obstructive sleep apnea (OSA) has been implicated in declarative memory impairment. Here, we evaluated immediate recall and overnight declarative memory in patients with suspected OSA before and after standard clinical management in a longitudinal cohort of 265 patients. Methods: A nocturnal polysomnographic study (PSG) was performed at baseline and repeated six months later. The Pictorial-Based Declarative Memory Questionnaire (PDMQ) was administered and consisted of four learning trials followed by free-recall 10 min before PSG and the following morning upon awakening. The primary cognitive endpoint was the change in pictorial declarative memory performance from baseline to 6-month follow-up, expressed as the number of correctly recalled items on the PDMQ. Results: Both immediate and delayed recall performances significantly improved in the no OSA/mild OSA and severe OSA groups, whereas only immediate recall improved in the moderate OSA group. In the severe group, comparisons between patients whose apnea–hypopnea index decreased to <30 events/hour and those whose AHI remained >30 revealed significant cognitive improvements in both subgroups, particularly in initial and late trials (Trials 1, 2, 5, 6). In multivariable models, baseline PDMQ performance and indices of SpO₂ desaturation and sleep fragmentation emerged as independent predictors of change in declarative memory. Conclusions: These findings suggest that routine clinical management of patients with OSA was accompanied by modest, albeit statistically significant improvements in declarative memory, and that both intermittent hypoxia and sleep fragmentation play important roles in memory change. Full article

The rapid integration of artificial intelligence (AI) into higher education marks a radical epistemic shift, unsettling long-held assumptions about how knowledge is made, taught, and judged. This paper argues that the theory of living structure offers a timely foundation for liberal arts and whole-person education in the era of AI. Living structure—Christopher Alexander’s term for the recurrent hierarchical order that makes environments feel alive—is treated here as two faces of one phenomenon: living, the right-brain perception of wholeness, and structure, the left-brain order that can be computed through fifteen geometric properties, two fundamental laws, two design principles, and the computable L- and B-scores. From this basis the paper develops a Living Structure + AI paradigm, a new episteme for higher education, deliberately so ordered because living structure is held to be more fundamental than AI: structure is the order of nature and culture, while AI is a tool that gives that order new expression. The argument is grounded in teaching practice led by LivableCityLAB, under its own teaching-research project and in partnership with Residential College 1, spanning architecture and city-science courses or theses, an undergraduate whole-person common-core course (Self and Wholeness), and a new postgraduate course (Experiential Learning: Living Structure + AI Inspired Design). Across these settings, students read built environments structurally, declare a skeleton, and use AI as a structural mediator while making and inhabiting real spaces. Across four campus renovations (total N = 33 students) and the two courses (N = 49 undergraduates; N = 7 postgraduates), structural scores (the L- and B-scores) rose in every renovated case, and these architectural and perceptual measures converged with preference tests and visual-attention analysis; course-embedded, rubric-based assignments provide complementary, though not psychometrically validated, evidence of students’ engagement with the paradigm. This paper closes by arguing that the deepest contribution of Living Structure + AI to liberal arts education is not on paper or on screens but down to earth—in the daily life spaces in which students learn to feel, measure, and remake wholeness. Full article

Physical literacy has become influential across education, sport, health, and recreation. Yet the field contains multiple definitions and distinct traditions rather than a single agreed position. One especially influential strand is the Whiteheadian account, the philosophically oriented tradition associated with the British philosopher and physical educationalist Margaret Whitehead and extended through allied writers and institutional work. Whitehead did not invent the term physical literacy, which has a longer history, but she provided its most influential contemporary philosophical reconstruction and helped shape its current international meaning. The Whiteheadian account has been important because it rejects narrow mind–body separation and offers a holistic, lifespan-oriented account of movement, meaning, and human flourishing. The argument advanced here is that the Whiteheadian account is non-dualist in declaration but not always in operation. Its explicit commitment to monism and lived embodiment is not always matched by its practical grammar, in which bodily competence, bodily participation, and visible movement often carry more pedagogical and evaluative weight than minded engagement as a process of learning. Radical embodied cognitive science, especially radical enactivism, offers additional conceptual resources for developing a more explicitly relational account of learning and physical literacy because it begins with situated organism–environment engagement rather than with the later integration of bodily and mental domains. The article concludes by proposing a more relational, process-oriented, and pedagogically robust understanding of physical literacy. Full article

Which runtime governance mechanisms reduce physical risk when a learned controller drives a building’s climate, and under what conditions? We develop a closed-loop software-in-the-loop testbed in which a setpoint model trained on real occupancy data drives a physics-based thermal zone through a declarative governance plane, with outcomes scored by an independent safety oracle, and we run the same governance logic on a real MQTT stack with an in-process policy decision point and a hash-chained audit log. Under distribution shift, admission control reduces unsafe physical exposure by $19.4\%$, from 1185.3 to 954.8 °C·min, whereas adding checkpoint rollback reduces it by only a further $0.2\%$ in the reference run ($0.1$–$0.4\%$ across sensor noise seeds): the governance decision takes 0.44 ms while physical recovery takes a median of 61 min. Prevention therefore outperforms recovery in the studied thermal system, and the remaining avoidable exposure is driven by the policy’s estimate of occupancy context. A deterministic single-rule thermostat incurs $50\%$ more exposure under shift while the learned controller uses a $38\%$ higher heating demand proxy: a safety–demand trade-off, not evidence that learned control is necessary. A plant sweep yields an operating envelope criterion for inertial plants: rollback contributes materially to safety only when the plant is restored before the next command arrives and sampled before it can leave the safe set; on slower plants it removes at most $14.7\%$, with a transition band in between. No physical hardware was operated. Full article

Green low-carbon data centers operate as coupled cyber-energy systems whose dispatch must coordinate renewable generation, grid exchange, battery storage, cooling load, flexible computing workload, carbon-intensity signals, and reliability constraints. This study develops and evaluates a safety-constrained deep reinforcement learning framework for source–load–storage coordinated operation of a grid-connected green data center. The operating problem is formulated as a constrained Markov decision process with state variables describing the IT load, deferrable workload backlog, renewable availability, electricity price, marginal carbon intensity, battery state of charge, server-room temperature, reserve margin, and calendar context. The action space covers grid import and export, renewable utilization, storage charge and discharge, workload shifting, and cooling control. The learning architecture combines a constrained actor–critic policy, adaptive Lagrangian safety critics, and a control barrier function (CBF)-based action shield that projects unsafe actions onto an explicitly defined operating set before plant execution. The shield is specified as a low-dimensional quadratic projection over state-dependent SOC, thermal, reserve, SLA, and grid-interface constraints, while cumulative risks are priced through Lagrangian safety budgets during policy training. The evaluation uses a controlled and auditable benchmark simulation with normalized public-data-compatible profiles, declared scenarios, random seeds, neural-network settings, and mechanism-matched baselines; it is not a telemetry-based verification or hardware certification of a deployed data center. Within this declared benchmark, the proposed safe DRL controller produces a simulated 13.1% emission reduction relative to the Rule-based controller, 95.8% renewable utilization, a normalized annual cost of 0.91, and fewer boundary contacts than the tested unconstrained, Lagrangian-only, and shield-only PPO variants. These percentages are simulator outputs relative to the stated benchmark and must not be interpreted as measured field savings. The results show how separating reward learning, cumulative safety pricing, and one-step engineering projection changes low-carbon dispatch within the specified model. Full article

This study examines the effectiveness of a virtual reality (VR) application as a learning tool in higher hospitality education, focusing on declarative knowledge acquisition and test-based learning outcomes. Conducted as a classroom-based pilot study, it involved a census of undergraduate students enrolled in a restaurant management course (N = 28) and compared VR-supported learning with traditional instruction using printed materials. Declarative knowledge acquisition was assessed using identical multiple-choice pre- and post-tests. Results showed that scores improved across all students. A statistically significant time × group interaction indicated that the two groups improved at different rates over time. Students who learned using printed materials demonstrated greater improvement than those who used the VR application. The findings suggest that, in its implementation, the VR application did not demonstrate superior test-based knowledge outcomes compared to traditional learning. One possible explanation lies in the type of knowledge assessed: the test focused on declarative and recognition-based knowledge, whereas VR may be more effective for procedural and experience-based learning. The limited interactivity of the early-stage VR application (VR HOTEL v0.9.4) may have also constrained its instructional potential. Overall, the results highlight the importance of aligning VR-based learning activities with learning objectives, instructional design, and assessment methods. Full article