Search Results (1,418)

Classic machine learning and regime identification methods applied to financial time series lack theoretical guarantees and exhibit systematic failure modes: heavy-tails invalidate moment-based geometry, rendering distances and centroids dominated by extremes or unstable; jumps violate smoothness, destabilizing local regressions, kernel methods, and gradient-based learning; and non-stationarity disrupts neighborhood relations, so distances in classical feature spaces no longer reflect meaningful proximity. To address these challenges, we propose a topology-based machine-learning framework grounded on probabilistic reconstruction of state-space geometry, which replaces moment- and smoothness-dependent representations with deformation-stable summaries of state-space geometry, preserving neighborhoods, adjacency, and topology. The finite-sample validity of homeomorphic state-space reconstruction, required for topology-based machine learning, is assessed through numerical studies on synthetic data with heavy tails, jumps, and known ground-truth regimes. Further diagnostics of local invertibility and bounded geometric distortion quantify when embedding windows are consistent with local diffeomorphic behavior, enabling metric-sensitive, geometry-aware learning. Clustering of Hilbert-space summaries accurately recovers underlying market tail-risk regimes with robust results across selected filtrations. Temporal, feature-space, and cluster-label null tests confirm that topology-based clustering captures genuine topological structure rather than noise or artifacts, and encodes temporal dependencies at local, mesoscopic, and network levels associated with market regimes. Full article

This article examines how artificial intelligence and algorithmic systems are reconfiguring truth regimes in digital societies, introducing the concept of “Artificial Truth” to describe an emerging form of epistemic governance where knowledge production and validation become infrastructural functions of sociotechnical systems. The study develops an integrated theoretical framework combining Foucault’s notion of truth regimes, Bourdieu’s theory of symbolic capital and fields, and Actor-Network Theory’s constructivist approach. Through conceptual analysis, the article investigates how algorithmic recommendation systems, generative AI, and automated fact-checking operate as epistemic devices that actively shape what is recognized as credible, authoritative, and true in public discourse. The analysis reveals three fundamental transformations: (1) the restructuring of trust economies, with epistemic authority shifting from institutional expertise to platform-native capital based on engagement metrics and affective proximity; (2) the emergence of generative AI as an epistemic actor producing “synthetic truth” through linguistic fluency rather than propositional understanding; (3) the institutionalization of computational veridiction in algorithmic fact-checking systems that translate situated epistemic judgments into probabilistic classifications presented as neutral. These dynamics configure a regime where truth is evaluated less by correspondence with reality and more by computational plausibility and platform integration. The article’s primary contribution lies in providing a unified theoretical framework for understanding contemporary transformations of epistemic authority, moving beyond disinformation studies to analyze AI as an epistemic actor. By integrating classical sociological perspectives with Science and Technology Studies, it conceptualizes algorithmic systems as epistemic infrastructures that embody specific power relations, restructure symbolic capital economies, and distribute epistemic authority asymmetrically, with profound implications for democratic knowledge, citizen epistemic agency, and public sphere pluralism. Full article

Evolutionary reinforcement learning (ERL) offers a compelling alternative for continuous control by combining the population-level exploration of evolutionary algorithms with the gradient-based exploitation of reinforcement learning. However, applying conventional genetic operators to deep networks can be highly destructive, often inducing abrupt behavioral shifts that erase previously learned skills. Proximal distilled evolutionary reinforcement learning (PDERL) addresses this issue with phenotype-aware operators, leveraging proximal mutation and distillation crossover to produce safer and more constructive variations. Despite these advances, PDERL and many ERL frameworks still exhibit a fundamental evaluation asymmetry: an evolving actor population is guided by a single, centralized critic for fitness evaluation and action filtering. This single-critic dependence creates a bottleneck and a potential single point of failure, where bias or instability in value estimation can misdirect the evolutionary search. To overcome this limitation, we propose co-evolutionary proximal distilled evolutionary reinforcement learning (Co-PDERL), a heterogeneous dual-population framework that co-evolves both actor and critic populations. Co-PDERL extends phenotype-aware evolution to the value-function landscape via a loss-filtered distillation crossover and a Jacobian-based proximal mutation tailored for critics, and employs a condition-gated synchronization mechanism to enable robust bidirectional knowledge transfer between the evolutionary populations and the reinforcement learning agent. Experiments on MuJoCo continuous control benchmarks show that Co-PDERL outperforms competitive baselines on most tasks, including standard ERL and PDERL, improving both sample efficiency and asymptotic performance by effectively alleviating the single-critic bottleneck. Full article

As a key spatial platform for implementing China’s Northeast Revitalization Strategy, coordinated development of production–living–ecological (PLE) functions in the Changchun Metropolitan Area is crucial for high-quality regional development. This study uses 24 counties (districts) in the metropolitan area as analytical units and develops a quantitative indicator system to evaluate PLE functions. We integrate the entropy-weighted TOPSIS method, social network analysis (SNA), and geographically and temporally weighted regression (GTWR) to examine the spatiotemporal dynamics, spatial correlation networks, and driving mechanisms of the three functions from 2013 to 2023. Temporally, the production function follows a growth–decline–recovery trajectory, the living function increases overall despite fluctuations, and the ecological function strengthens continuously. Overall, the three functions increasingly exhibit coupling and synergy. Spatially, the production function concentrates in core areas and diffuses along major axes. The living function is led by the core and followed by county-level catch-up. The ecological function is higher in the east, relatively stable in the west, and connected by corridors, together forming a multi-center, axis-based synergistic pattern. In the spatial correlation networks, densities of the production and ecological networks remain largely stable, whereas the living network becomes markedly denser. The three networks display distinct topologies and continue to evolve structurally. For driving mechanisms, the GTWR model provides the best fit. Geographic proximity positively contributes to the formation of all three functional networks, while the eight explanatory factors show pronounced spatiotemporal heterogeneity. These findings provide an evidence base for optimizing functional coordination and implementing differentiated spatial governance in metropolitan areas. Full article

Human organoids and organ-on-chip/microphysiological systems (OoC/MPS) are increasingly used as new-approach methodologies for biotoxin assessment. They retain human-relevant tissue organization and enable interpretable analysis of exposure geometry, barrier transport, perfusion, and (when needed) multi-organ coupling. In this review, we synthesize primary evidence across major toxin classes, including bacterial enterotoxins (e.g., cholera toxin, heat-stable enterotoxins, Shiga toxins), mycotoxins (e.g., aflatoxin B1, ochratoxin A, deoxynivalenol), and algal/cyanobacterial toxins (e.g., saxitoxin, domoic acid, microcystins, biliatresone). We emphasize studies that clearly define toxin identity and exposure context and that demonstrate mechanism-critical model competencies under assay conditions. We highlight decision-informative functional endpoints that align with the dominant pathophysiology. These include cystic fibrosis transmembrane conductance regulator (CFTR)-dependent secretion in human enteroids/colonoids, transporter-linked proximal tubular injury in kidney MPS, gut–kidney axis injury from Shiga toxin-producing E. coli in microfluidic systems, and multi-electrode array (MEA) network readouts in human 3D neural tissues. We then summarize best practices that improve cross-study comparability. These include reporting delivered versus nominal exposure, assessing recovery/mass balance and device/material interactions, applying proportional biological qualification (polarity, transporter/enzymatic competence, functional stability), defining a minimal comparable endpoint core, and preserving QIVIVE readiness in reporting. Finally, we outline near-term priorities for the field, including chronic low-dose and mixture designs, harmonized reference panels and acceptance criteria, and fit-for-purpose escalation to coupled OoC/MPS only when perfusion or organ–organ coupling is expected to change the interpretation. Full article

Dissolved oxygen (DO) is a crucial indicator for characterizing water quality and ecosystem status in freshwater lakes, and its concentration is closely correlated with the surrounding aquatic environment, particularly meteorological conditions. However, traditional DO prediction methods struggle to effectively capture the intricate coupling relationships between multi-station meteorological factors and DO concentration time series, limiting the prediction accuracy. This study proposes a multi-scale spatio-temporal graph neural network with integrated multi-meteorological factors. Taking Taihu Lake and its surrounding cities as the study area, a meteorological graph is constructed based on the geographic proximity between meteorological stations, and a dual-stage “local–global” modeling strategy is adopted to capture the spatio-temporal dependencies of DO concentration under meteorological forcing. Using R², RMSE, MAE and MAPE as evaluation metrics, we conducted single-step and multi-step DO prediction experiments on the 2023–2024 Taihu Tuoshan water quality dataset and compared the proposed model with commonly used prediction models. In the single-step prediction task, the proposed model improved R² by 2.12–20.84% and reduced RMSE, MAE, and MAPE by 3.05–40.80%, 14.97–53.26%, and 6.91–55.62%, respectively. In the 6-step-ahead and 12-step-ahead prediction tasks, RMSE and MAE were reduced by 3.79–15.75% and 6.68–23.09%, and by 5.03–10.39% and 7.13–16.46%, respectively. The experimental results provide quantitative evidence for the superiority of the proposed model in single-step and multi-step DO prediction. This study offers a novel data-driven tool for lake water quality early warning and drinking water safety, and the proposed framework can serve as a reference for water quality prediction studies driven by multi-source environmental factors. Full article

Intra-urban commuting plays a fundamental role in shaping urban spatial structure and daily mobility patterns. Existing studies have largely explained commuting flows using attribute-based or distance-centred approaches. Such approaches overlook the interdependent and relational nature of commuting within complex urban systems. This study constructs a subdistrict-level commuting network using anonymised mobile phone signalling data from Hangzhou, China, and a valued exponential random graph model (valued ERGM) to examine how commuting flows are generated through the interaction of network self-organization, local job-housing conditions, and multi-dimensional proximity. The results reveal strong endogenous dependence exemplified by reciprocal commuting ties. Employment agglomeration and public rental housing provision are associated with stronger integration of subdistricts within the commuting network, while high housing prices and certain residential amenities are associated with reduced inter-subdistrict commuting. Beyond geographic distance, metro connectivity, administrative affiliation, and social interaction are significantly associated with commuting flows. This study advances a relational explanation of intra-urban commuting and demonstrates the methodological value of valued ERGMs for analysing weighted urban flow networks. The findings have implications for integrated transport, housing, and governance strategies, particularly transit-oriented development, cross-jurisdictional coordination, and the strategic siting of affordable housing, aimed at promoting more locally embedded and sustainable urban mobility. Full article

In low-Earth-orbit (LEO) satellite networks, the need for intelligent parameter-adjustment strategies has become increasingly critical due to the presence of highly dynamic channel conditions, limited spectrum resources, and complex interference environments. In this paper, a method for optimizing LEO satellite communication links based on deep reinforcement learning (DRL) is proposed. Through the optimization of the transmit power, the modulation and coding scheme (MCS), the beamforming parameters, and the retransmission mechanisms, adaptive link control is achieved in dynamic operational scenarios. A multidimensional state space is constructed, within which the channel state information, the interference environment, and the historical performance metrics are integrated. The spatio-temporal characteristics of the channel are extracted by means of a hybrid neural architecture that incorporates a convolutional neural network (CNN) and a long short-term memory (LSTM) network. To effectively accommodate both continuous and discrete action spaces, a hybrid DRL framework that combines proximal policy optimization (PPO) with a deep Q-network (DQN) is employed, thereby enabling cross-layer optimization of the physical-layer and link-layer parameters. The results demonstrate that substantial improvements in throughput, bit error rate (BER), and transmit-power efficiency are achieved under severely time-varying channel conditions, which provides a new idea for resource management and dynamic-environment adaptation in satellite communication systems. Full article

Unmanned Aerial Vehicle (UAV)-assisted mobile edge computing is pivotal for the Space–Air–Ground–Sea Integrated Network (SAGSIN) to support heterogeneous task offloading. However, the inherent resource constraints of UAVs limit their ability to support intensive and concurrent task processing in dynamic environments. In such complex scenarios, the dual requirements of discrete model partitioning and continuous bandwidth allocation make it difficult for traditional reinforcement learning algorithms to achieve optimal resource matching. Therefore, in this paper, we design a joint optimization framework based on Asynchronous Advantage Actor-Critic (A3C) and proximal policy optimization (PPO). Specifically, the model partitioning strategy is learned through PPO, which utilizes a clipped objective function to ensure training stability and generalization across complex Deep Neural Network (DNN) structures. Moreover, the framework leverages the asynchronous multi-threaded architecture of A3C to dynamically allocate bandwidth, effectively accommodating rapid fluctuations in terminal access. Finally, to prevent resource monopolization and ensure fairness, a weighted priority scheduling mechanism based on task urgency and computation time is introduced. Extensive simulations show that the proposed algorithm outperforms existing approaches in terms of task completion rate, task processing latency, and resource utilization under dynamic SAGSIN scenarios. Full article

Accurate pedestrian trajectory prediction and intention estimation are crucial for autonomous systems and intelligent transportation applications. However, existing methods often address these two highly correlated tasks in isolation and rely on static or heuristic interaction modeling, leading to insufficient adaptability and limited generalization capability in dynamic traffic scenarios. To this end, this paper proposes MTG-TPNet, a Multi-task dynamic Graph Transformer network for joint Trajectory Prediction and intention estimation. The research framework integrates three key innovations: First, a dynamic graph neural network enhanced with motion features, whose graph topology can be adaptively learned end-to-end based on semantic and motion contexts to accurately capture evolving interactions. Second, a multi-granularity attention mechanism that collaboratively fuses geometric proximity, semantic similarity, and physical hard constraints to achieve fine-grained modeling of spatiotemporal dependencies. Third, a dynamic correlation loss based on Bayesian uncertainty, which balances multi-task learning in an adaptive manner and encourages beneficial interactions across tasks. Extensive experiments on the publicly available PIE and ETH/UCY datasets demonstrate that MTG-TPNet achieves state-of-the-art performance. On the PIE dataset, the proposed model significantly outperforms the best baseline model in trajectory prediction metrics, achieving an Average Displacement Error (ADE) of 0.21 and a Final Displacement Error (FDE) of 0.29. This represents a 27.6% reduction in ADE while maintaining stability in intention estimation. Systematic ablation studies validate the effectiveness of each proposed module, with the model retaining an average performance of 69.3%. Furthermore, cross-dataset evaluations confirm its superior generalization capability. This study provides a powerful unified framework for robust pedestrian behavior understanding in complex urban traffic scenarios. Full article

This paper investigates the strategies employed by local journalists to verify AI-generated and manipulated imagery during the 2026 Romagna earthquake. Drawing on a qualitative methodology, this study identifies a multi-layered process of “situated verification.” The findings reveal that verification efficacy is predicated on territorial familiarity, professional networks, and direct institutional triangulation, which collectively compensate for technological and resource constraints. Local journalists emerge as epistemic mediators who stabilize the information ecosystem, mitigate public anxiety, and curb the spread of disinformation. Furthermore, institutional interventions, such as police-led fact-checking, function as both pragmatic verification tools and symbolic signals that promote responsible information sharing. By highlighting how verification is deeply rooted in temporality, social embeddedness, and local expertise, this research underscores the critical role of proximity journalism in crisis communication. The study contributes to the fields of visual epistemology and media literacy, demonstrating that relational and context-aware practices are essential for maintaining information integrity in an era of AI-driven visual disinformation. Full article

This study examines the first corporate disclosures issued under the IFRS Sustainability Standards, with full alignment to IFRS S2, using natural language processing and text mining techniques, and contributes evidence to an underexplored phase of sustainability reporting research. Focusing on an emerging market setting, the analysis covers the 2024 reports of 18 firms included in the Borsa Istanbul Sustainability 25 Index. The reports are evaluated through readability metrics (Flesch–Kincaid, Gunning Fog, and SMOG), conceptual concentration measures (TF–IDF), semantic proximity analysis (Cosine Similarity), and network-based methods. The findings indicate a strong degree of technical discipline and standard adherence in the first year of implementation, alongside a pronounced barrier to linguistic accessibility. Average Gunning Fog and Flesch–Kincaid scores of 18.94 and 14.90 suggest that meaningful interpretation of these disclosures requires advanced academic proficiency. The observed technical density reflects the detailed and standard-driven structure of IFRS-based sustainability reporting and points to a persistent tension between technical precision and interpretability, consistent with the Managerial Obfuscation perspective (H1). High levels of semantic overlap further indicate that, under conditions of reporting uncertainty, firms rely heavily on established disclosure patterns, reinforcing professional convergence through both coercive (regulatory alignment) and mimetic (uncertainty-driven emulation) isomorphism (H2). In contrast, distinct narrative configurations identified through principal component and network analyses are evaluated as potential credibility-enhancing signals within the framework of Signaling Theory (H3). Overall, IFRS Sustainability Standards reporting functions in emerging markets as a learning-oriented and strategically relevant disclosure mechanism that may potentially mitigate information asymmetry through its linguistic properties. Full article

Rapid, standardised discrimination of soil taxonomic units remains challenging when relying solely on conventional field descriptions and laboratory analyses, particularly at high sampling densities. This study evaluated whether proximal spectroscopy and hyperspectral imaging can support the classification of Brazilian Soil Classification System (SiBCS) suborders and pedogenetic horizons when surface and subsurface spectra are treated separately. Six intact soil monoliths (0.12 × 1.60 m) were collected in Paraná State, southern Brazil, representing one Organossolo (Ooy), three Latossolos (LVd, LVd1, and LVd2) and two Argissolos (PVAd and PVd). For each monolith, 800 spectra were acquired per sensor with a non-imaging VIS–NIR–SWIR spectroradiometer (350–2500 nm), and 800 spectra per sensor per monolith were extracted from the SWIR hyperspectral images (1200–2450 nm). Principal component analysis (PCA) was used to summarise spectral variability, and supervised classification was performed via k-nearest neighbours, random forest, decision tree and gradient boosting for suborders (10-fold cross-validation), and a neural network was used for within-profile horizon classification. PCA indicated that most of the spectral variance was captured by a dominant axis, with clearer separation among suborders in the SWIR space than in the full VIS–NIR–SWIR range. With respect to suborder classification, subsurface spectra outperformed surface spectra, and SWIR outperformed VIS–NIR–SWIR: the best accuracies were 0.96 for subsurface SWIR (gradient boosting; AUC = 0.99; MCC = 0.95) and 0.89 for surface SWIR (k-nearest neighbours; AUC = 0.98; MCC = 0.87). Within-profile horizon classification via VIS–NIR–SWIR achieved accuracies of 0.84–0.97 with the Neural Network, with most misclassifications occurring between adjacent horizons. Overall, subsurface SWIR information provided the most reliable basis for taxonomic discrimination, whereas horizon classification was feasible but reflected gradual spectral transitions along the profile. Full article

The increasing densification of cell-free massive multiple-input multiple-output (MIMO) networks makes access point switch on/off (ASO) a key mechanism for improving energy efficiency in future wireless systems. While reinforcement learning (RL) has been explored for ASO, differences in modeling assumptions and evaluation scope leave open questions regarding robustness and scalability. In this work, ASO is investigated from an explicit energy-efficiency perspective using a RL framework based on Proximal Policy Optimization (PPO). The policy learns state-dependent AP activation under partial observability using compact per-access point (AP) large-scale fading statistics and power parameters, without requiring instantaneous small-scale channel state information or combinatorial search, enabling practical online implementation. A comprehensive evaluation is conducted under a unified and reproducible simulation framework across three cell-free deployment scenarios of increasing size that preserve AP density while incorporating realistic channel and power consumption models. Performance is assessed through both average and distribution-based metrics. Numerical results show that the PPO-based policy consistently outperforms random activation and the all-on baseline, achieving energy-efficiency improvements of up to 66% and nearly 50%, respectively, while activating a comparable number of APs. Moreover, the learned policy maintains robust performance as the network scales, reducing the likelihood of highly energy-inefficient operating regimes. Full article

As the number of electric vehicles (EV) increases, the demand for recommending the best charging location when using a large-scale charge network to charge is also increasing. A successful recommendation will utilize the user’s preference and the operational constraints of the charging network to make sure that it also takes into account the real-time operational requirements of the network. Most current papers focus on optimizing individual algorithmic components in isolation; consequently, many of these papers neglect to provide a holistic view of an integrated system. In addition, there are many operational requirements that current research does not consider, such as cold-start personalization for new users and enforcing real-time operational constraints like station availability, power capacity, maintenance windows, etc. This paper describes a deployable multi-stage recommendation system that creates a candidate list based on location and ranks preferences based on user, station and context features. The recommendation system also adds a configurable rule-based re-ranking layer to ensure that both hard constraints (i.e., charger availability and power-cap limits) and soft objectives (i.e., load balancing and operator priority) are enforced. A method for enabling mixed use between stable Bayesian and adaptive Bayesian methods was developed to provide users starting with cold-start performance that do not have adequate histories. Evaluation of this method using 100k+ real charging sessions showed that the fraction of sessions where the ground-truth station appears in the top-two recommendations (Hit@2) for the recommendation system was 0.82, representing a 37% increase in performance compared to proximity-based recommendation methods. The online deployed recommendation system has a 99th-percentile serving latency (P99) of less than 200 ms. The findings of this paper provide a framework for the implementation of operationally-relevant user-centric recommendation systems for EV services at scale. Full article