Search Results (7,337)

Although canna (Canna edulis Ker) starch possesses high swelling power, it remains an underutilized resource. This study aimed to engineer highly porous, food-grade canna starch aerogels as carriers for cyanidin-3-glucoside (C3G), incorporating enzymatically modified starch fractions prepared via α-amylase hydrolysis followed by lyophilization. Moderate enzymatic modification (sample AG1) effectively tailored the aerogel architecture by selectively removing amorphous regions. This targeted hydrolysis yielded a highly interconnected, hierarchical porous network with a high porosity (92%). Importantly, although this architectural transformation increased the average macroscopic pore size, it preserved mechanical integrity, as evidenced by a compressive strength exceeding 4000 kPa. In contrast, excessive hydrolysis led to pore collapse and structural failure. The AG1 aerogel exhibited a markedly enhanced C3G equilibrium adsorption capacity (43.9 mg/g), outperforming the native starch aerogel (36.0 mg/g). Adsorption data adhered to pseudo-second-order kinetics, indicating that this model provided a better description of the adsorption process, while the underlying adsorption mechanism may involve interactions between C3G and the aerogel matrix, potentially including hydrogen bonding. These results suggest that controlled enzymatically hydrolysis may provide a useful strategy for modulating the hierarchical microstructure of canna starch aerogels, thereby supporting their potential as effective carriers for sensitive bioactive compounds in functional food systems. Full article

Femtosecond laser processing enables spatially controlled modification of the structure, composition, and functionality of advanced materials through highly localized energy deposition and laser–matter interaction mechanisms. This review discusses the role of ultrafast laser irradiation in the engineering of oxide-based functional systems, including functional oxides, oxide-containing layers, interfaces, and heterogeneous structures whose properties are substantially determined by an oxide component. The mechanisms governing laser-induced oxidation, phase transformation, elemental redistribution, defect generation, and hierarchical micro-/nanostructure formation are considered. Particular attention is given to the ability of femtosecond laser processing to create surfaces with tailored interactions with light, liquids, biological environments, and external stimuli, enabling responsive devices and advanced manufacturing strategies. Laser-modified oxide layers and nanostructured interfaces are analyzed as pathways for controlling surface energy, optical properties, chemical activity, and functional response. The relationship between laser-generated architectures and their applications in sensing, actuation, wetting control, and multifunctional systems is discussed. By connecting ultrafast laser surface engineering with emerging 4D manufacturing concepts, this review highlights femtosecond laser technologies as a versatile platform for designing systems with spatially programmed functionality and, where stimulus-dependent behavior is demonstrated, time-dependent performance. Such approaches provide opportunities for integrating adaptive oxide-based functional systems into advanced manufacturing. Full article

A prescribed time-adaptive event-triggered sliding mode control method is proposed for a second-order aircraft antiskid braking system with unmeasurable longitudinal velocity, subject to unknown actuator faults and external disturbances. Based on the time scale transformation technique, a prescribed-time observer is constructed to estimate the unmeasurable longitudinal velocity. A practical prescribed-time super-twisting observer with a saturated gain is designed to estimate the disturbance. Within the prescribed time convergence framework, an adaptive update law and a nonsingular integral sliding surface are developed to compensate for actuator faults. Building on this, a time-varying dynamic threshold event-triggering mechanism is incorporated into the prescribed time-sliding mode control process, while excluding Zeno behavior and reducing the control update frequency. The aforementioned prescribed-time observers and the event-triggered adaptive sliding mode controller form a strict temporal hierarchical architecture. Based on Lyapunov stability theory, it is proved that the closed-loop system is practically prescribed-time stable and that all closed-loop signals are uniformly ultimately bounded. Comparative simulation results verify the effectiveness of the proposed method. Full article

Hyperspectral image classification relies heavily on the effective modeling of spatial–spectral representations. Recent deep learning architectures, including Transformers and state space models (SSMs), have shown promise for HSI classification. However, under few-shot scenarios, they may suffer from optimization instability in early-stage feature reduction, weakened local spatial–spectral correlations after direct sequence flattening, and attenuation of center-pixel spectral information caused by deep spatial aggregation. To mitigate these issues, we propose orthogonal projection spatial–spectral Mamba (O-Mamba), a lightweight architecture for few-shot HSI classification. First, we introduce a task-driven orthogonal projection module (TOPM) for learnable end-to-end spectral dimensionality reduction. In this module, orthogonal parameterization, supervised initialization, and an auxiliary loss jointly improve the stability of the projection process, reducing feature redundancy and mitigating representation collapse. Second, we design a 3D spatial–spectral Mamba encoder that employs 3D Convolutional Neural Networks (CNN) as local tokenizers to preserve local spatial–spectral structures and then uses Mamba to capture long-range sequence dependencies with linear complexity with respect to sequence length. Finally, to alleviate over-smoothing in the target-pixel representation, we propose a decoupled target–context fusion strategy. This mechanism separately preserves the original spectral signature of the center pixel and fuses it with high-level contextual features, which may improve the separability of spectrally similar classes. Extensive experiments on four benchmark datasets show that O-Mamba achieves competitive classification performance under the evaluated few-shot settings, while maintaining a relatively small model size and low computational cost compared with representative CNN, Transformer, and Mamba-based methods. Full article

With the continued advancement of low-carbon campus transformation and the increasing penetration of renewable energy, campus integrated energy systems have become key infrastructure for green campus development. However, the highly random nature of student behavior causes dynamic fluctuations in electricity, heating, and cooling loads, creating major challenges for real-time supply-demand balance and economic system scheduling. To address this problem, this paper takes student behavior uncertainty as the core disturbance factor and proposes a flexible architecture-driven autonomous adaptation and multi-energy complementary optimization strategy. A closed-loop operation paradigm of signal–response–complementarity–regulation is established, in which dynamic electricity price signals, comfort-oriented guidance, and campus functional energy-zone division are combined to form a multi-level autonomous response chain. To improve solution efficiency, the electromagnetic wave propagation algorithm is further enhanced, and a Multi-Objective Electromagnetic Wave Propagation Algorithm (MEMWPA) is developed. Wave-impedance matching and energy-flux-density feedback mechanisms are introduced to strengthen convergence performance in complex multi-objective optimization problems. Comparative case studies show that the proposed strategy can effectively smooth the net load curve, reduce the campus peak load by 26.73%, and increase the load factor by 14.533 percentage points, thereby improving both operational flexibility and energy efficiency. Full article

Oriented object detection (OOD) in remote sensing images (RSIs) suffers from insufficient feature representation caused by arbitrary rotation angles and small spatial resolutions. Existing spatial–frequency fusion paradigms merely implement single-granularity feature interaction, either global image-level frequency compensation or local instance-level feature refinement, and fail to simultaneously capture global scene semantic consistency and local object fine-grained discriminability. In this paper, we propose a unified dual-level spatial–frequency collaborative detector (DSCDet) for remote sensing OOD tasks. Different from previous decoupled designs, the proposed DSCDet constructs a complete spatial–frequency collaborative fusion paradigm that shares a generic wavelet-based frequency extraction mechanism and cross-feature fusion module, which is adaptively deployed at both image-level and instance-level granularities. Specifically, our method introduces Haar wavelet transform to extract multi-scale frequency mutation features. On this basis, a generic cross-domain attention fusion (GCDAF) is constructed with granularity-dependent positional encoding constraints. The core difference between dual granularity fusion lies in geometric positional encoding, where image-level fusion adopts global scene positional embedding to maintain overall semantic stability, and instance-level fusion leverages local pairwise instance positional embedding to optimize fine-grained target feature interaction. The unified dual-level fusion architecture comprehensively integrates global semantic integrity and local target specificity, forming a robust and universal spatial–frequency feature representation system. Extensive experiments on three public remote sensing datasets, including DOTA-v1.0, DOTA-v1.5 and DIOR-R, demonstrate that the proposed DSCDet achieves competitive and superior performance against state-of-the-art OOD detectors. Full article

Automated pulmonary auscultation demands rapid and reliable anomaly detection. Contemporary deep learning frameworks frequently face deployment barriers due to their reliance on memory-intensive Transformer mechanisms and high-cost processing hardware. Addressing this limitation, the present study introduces the Neuro Scatter Mamba Kolmogorov–Arnold Neural Network (NSMK-Net), a lightweight, Transformer-free architecture. The model integrates 1D Wavelet Scattering, bi-directional Selective State Space Models (Mamba), and Kolmogorov–Arnold Networks (KAN). By substituting quadratic self-attention with continuous-time differential discretization, the framework achieves very good computational efficiency under severe hardware constraints. Model optimization followed an eco-friendly “Green-AI” methodology, successfully converging on a standard 4 GB VRAM graphics unit. Regarding real-world deployment, the finalized architecture can be considered as a possible candidate for future “Edge-AI” applications, because it requires only 0.34 MB of parameter storage (89,342 parameters) and executes inference in approximately 48 milliseconds per respiratory cycle. Evaluated on the SPRSound dataset, the proposed model achieved a cycle-level accuracy of 84.67% (Macro-F1: 0.48). When tested under the strict official 60/40 partition of the ICBHI 2017 dataset, the network delivered a global accuracy of 41.56% (Macro-F1: 0.31) alongside an official reported ICBHI Score of 49.38%. These metrics indicate a stable detection capability when processing highly imbalanced clinical data. By replacing fixed activation nodes with learnable edge non-linearities and utilizing linear sequence memory, this new structural approach reduces the dependency on high-end hardware for medical acoustic processing. Full article

Anyone who has watched a distant scene shimmer above hot pavement has seen atmospheric turbulence destroy image detail. In long-range imaging, turbulence produces spatially varying blur, geometric warping, scintillation, and temporal instability. Recovering the underlying scene is therefore an ill-posed inverse problem, and learned priors must compensate for distortions that simplified optical models capture only partially. We use turbulence mitigation as the umbrella term for all countermeasures and turbulence restoration for its computational core, the estimation of a clean image from degraded observations. From a cognitive-computing perspective, mitigation is not merely image enhancement. It is an uncertainty-constrained visual inference problem in which an intelligent system must reconstruct, interpret, and act on observations relayed through a stochastic physical channel. This critical review examines how the deep learning era has reshaped turbulence mitigation, with physics as the foundation for understanding degradation and designing inductive biases. It traces the architectural progression from convolutional and adversarial networks to Transformers, denoising diffusion models, Mamba and other state-space architectures, and physics-informed frameworks. For each family, we ask a common question: How does it treat the aleatoric uncertainty intrinsic to a random optical channel and the epistemic uncertainty introduced by scarce and simulator-dominated training data? The review also analyzes datasets, simulation strategies, loss functions, and evaluation metrics, and it separates the small body of shared-protocol benchmark evidence from the far larger body of self-reported results that cannot be compared across studies. Persistent obstacles include the synthetic-to-real domain gap, the scarcity of paired real turbulence data, the mismatch between fidelity metrics and downstream task performance, and the computational cost that limits operational deployment. We close with an AI-centered agenda in which uncertainty quantification stands alongside domain adaptation as a first-order priority. Full article

To achieve a lightweight and high-stiffness design of robotic arms for construction robots, this paper proposes a novel data-driven generative design framework that integrates topology optimization, 3D generative adversarial networks (GANs), reverse engineering, and additive manufacturing. This paper develops a three-dimensional deep generative model that integrates Topology Optimization (TO) with Generative Adversarial Networks (GANs) to result in more efficient outcomes. A high-fidelity CAD model of a construction robotic arm was first established, from which a diverse geometric dataset containing 350 topology optimized models was generated. Subsequently, a 3D-GAN architecture was trained on this dataset to synthesize high-performance voxelized structural configurations, which were then transformed into smooth solid models via a streamlined reverse engineering workflow. Finally, the representative joint model achieved a mass reduction of approximately 51.67% and 28.93% compared to the initial model and topological model, while maintaining mechanical performance. Furthermore, physical prototypes were successfully fabricated using 3D printing technology, confirming the geometric compliance and manufacturability of the generated models. This work demonstrates the feasibility and effectiveness of combining generative deep learning with computational topology optimization and additive manufacturing for the intelligent design of construction robot components. Full article

Ordinary architectural conditions interact through arrangements that static representations often detach from time and use. This study examines six selected Turkish popular films as a mediated comparative corpus of apartments, neighborhood interfaces, mobile (route-vehicle) interiors, and domestic spaces in use. Comparative visual–spatial analysis of 24 scene-clusters traces how spatial domains and boundary/connection devices organize visibility, audibility, access, movement, bodily proximity, and collective attention. We define architectures of exposure as an event-level mismatch between scene-supported expected control over sight, sound, access, or bodily distance and the interactional field enabled by a configuration. A provisional, construction-corpus-derived layered model separates four primary spatial domains from boundary/connection devices, six interactional mechanisms, four control relations, three intensifiers, and contingent outcomes. Ten clusters directly demonstrate the mismatch; three show strategic or transformative widening, six provide partial or qualified evidence, and five delimit the concept through intended permeability or retained control. Cross-case comparison shows that the same device can preserve refusal, transmit distress, enable rescue, or support solidarity, while comparable spatial mechanisms acquire different narrative and ethical significance under comic and non-comic framing. The study contributes a scene-cluster method for treating fiction film as mediated architectural evidence and a diagnostic framework for future observation, acoustic assessment, visibility analysis, and post-occupancy research. Full article

Urban landscapes are increasingly understood as dynamic systems in which natural, cultural, and socio-spatial layers continuously overlap and evolve. Within this perspective, heritage and memory are often treated as stable qualities of place, to be preserved or restored amid ongoing urban transformation. This paper challenges that static understanding by advancing memory-in-transformation, a theoretical framework positioned within the broader concept of Temporal Urbanism. Drawing on an integrative synthesis of landscape theory, critical heritage studies, memory studies, and urban theory, the paper argues that urban landscape transformation does not simply affect heritage and memory but actively produces, reconfigures, and redefines them over time. The framework rests on three interrelated dimensions: temporal layering, mediated interpretation, and dialectical production, through which transformation operates as a mediating process linking spatial change, collective memory, and the continuous formation of heritage landscapes. Illustrative cases (Superkilen, Copenhagen; the Slussen redevelopment, Stockholm) show how transformation can destabilize existing heritage while generating new heritage systems. The paper further introduces the notion of temporal justice, foregrounding whose memories are sustained or marginalized in processes of change, and outlines new directions for research and practice in heritage urbanism, land-use planning, landscape architecture, and sustainable urban development. Full article

We present ESNformer, a hybrid architecture that couples an Echo State Network (ESN) reservoir with a Transformer encoder for classification of structured, multi-indicator assessment data: a fixed-order vector of complementary indicators per assessment instance rather than a repeated-measures time series. The reservoir acts as a fixed nonlinear feature map over the indicator vector, while self-attention, made position-aware over the fixed column order, learns how each indicator’s evidence contributes to the final decision, so the two components, together, capture local, indicator-level detail and global, cross-indicator interactions within a single, end-to-end trainable model. Interpretability is treated as a first-class design requirement rather than an afterthought: the architecture is paired with an explainability layer combining SHAP feature attribution (reported both globally and per class), the model’s own attention weights, a deletion/insertion faithfulness test that quantitatively verifies which inputs the model actually relies on, and counterfactual maps that translate a prediction into an actionable, inspectable recommendation. We evaluate the architecture on a concrete case study, classifying Braille-literacy instructional recommendations from 15 pedagogical indicators grouped into three categories (Mangold’s, ABKL, and Progresar), using a benchmark of 900 real assessment instances (630 used, together with a class-conditional augmentation procedure, to build a 2100-instance training set) with validation and test partitions (135 instances each) kept exclusively real. On this benchmark, the tuned model reached 85.33% accuracy, 85.90% macro-precision, 85.33% macro-recall, an F1 score of 85.25%, and an AUC of 0.95 on the real test set. SHAP attribution, attention weights, and the faithfulness test converge on the same two dominant indicators (response time and error count): removing them alone collapses accuracy to chance, while retaining only them recovers most of the model’s accuracy. We report this transparently alongside a comparison against ESN-only, Transformer-only, and tabular baselines (logistic regression, decision tree, random forest, XGBoost, and an MLP) on the same data and discuss what the hybrid architecture and its explainability pipeline add beyond what the two dominant indicators already explain and how the approach generalizes to other tabular and mixed-granularity assessment settings that require both predictive accuracy and a verifiable account of what drove each decision. Full article

Background/Objectives: Blood–brain barrier (BBB) permeability is a major practical obstacle in central nervous system (CNS) drug discovery, because only a small fraction of drug-like molecules achieve sufficient brain exposure. Methods: We present DeepBBB, a graph-based, data-composition-aware screening workflow for predicting BBB permeability and for constructing BBB-focused screening libraries from commercial chemical space. Rather than introducing a new graph-learning architecture, the workflow combines standard graph convolutional and graph-transformer models with deliberate control of training-set composition, commercial-library filtering, chemical-space profiling, and prospective experimental evaluation. Three model variants were trained on the Blood–Brain Barrier Database (B3DB): a baseline classifier/regressor pair (DeepBBB_V1_BC/RG), a variant trained with a more strongly negative-enriched configuration (DeepBBB_V2_BC), and a graph-transformer counterpart (DeepBBB_trans_BC/RG). Because the sample-level split assignments and per-compound predictions from the original runs were not recoverable, the archived summary metrics are reported descriptively in the main text and are not used to support calibration, scaffold-level validity, or generalization. Applying the workflow to the ChemDiv collection (~1.5 million compounds) and the Enamine REAL lead-like space (~1.7 billion compounds) produced three progressively more stringently filtered BBB-focused libraries (21,991; 4,808,885; and 151,790 compounds). Results: Analysis of available processed data indicated that the predicted BBB-permeable set occupies a compact, BBB-compatible property region. Physicochemical, fragment, and scaffold summaries were interpreted descriptively at the constructed-library level. In a first prospective campaign, one of 12 tested candidate compounds was PAMPA-BBB-positive (all-tested molecular-level positive fraction 8.3%; exact 95% CI 0.2–38.5%). In a second campaign, five of 35 tested candidate compounds were PAMPA-BBB-positive (14.3%; exact 95% CI 4.8–30.3%); 13 compounds were not quantifiable and were not treated as ordinary CNS-negative measurements, and the two campaigns differed in compound source, selection strategy, and assay setting, so the numerical difference is reported descriptively rather than causally. Conclusions: Together, these results support the feasibility of BBB-focused computational filtering and a PAMPA-BBB evaluation workflow for CNS-oriented discovery. Full article

This paper presents a comparative study of two approaches for solving second-order ordinary differential equations arising from the membrane theory of shells of revolution. The considered equations originate from the rotational symmetry of shell structures, which enables the reduction of the governing partial differential equations to a sequence of ordinary differential equations corresponding to individual circumferential harmonics. The study compares the classical Differential Transform Method (DTM) with Physics-Informed Neural Networks (PINNs). Both initial value and boundary value problems are investigated, including benchmark examples with known analytical solutions and a systematic analysis of the influence of PINN architecture on the solution accuracy. For the PINN approach, the effects of the number of collocation points, hidden layers, and neurons per layer on the approximation error and training time are examined. The results demonstrate that DTM provides an efficient framework for constructing analytical solutions of initial value problems with minimal computational cost. However, its application to boundary value problems requires the introduction of additional auxiliary parameters and the solution of supplementary nonlinear equations, considerably increasing the analytical complexity of the procedure. In contrast, PINNs achieve high accuracy for both initial and boundary value problems while naturally incorporating boundary conditions through the loss function. The presented results demonstrate how the exploitation of geometric symmetry, combined with modern scientific machine learning techniques, provides an effective computational framework for solving differential equations arising in shell mechanics. Full article

Eye diseases, particularly glaucoma and cataracts, are the leading causes of visual impairment, compromising quality of life. Automatic classification of these diseases can lead to more accurate and timely diagnosis, thereby limiting their progression and complications. In recent years, advances in Deep Learning (DL) have shown promising results in the study of images in ophthalmology. However, traditional DL models are based on a centralised approach to data, sharing sensitive patient information and compromising privacy; moreover, the models are often difficult to interpret. In this paper we propose a method aimed to solve the issues of privacy and transparency in decision-making related to eye diseases detection and localisation. As a matter of fact, we consider Federated Learning (FL), an approach based on data decentralisation that enables collaborative learning between different clients and sends only the model weights to the central server. In this way, sensitive patient data are not shared, ensuring security and privacy. With regard to eye disease classification we exploit a Vision Transformer, which allows global relationships within retinal images to be highlighted, improving representation capabilities compared to traditional convolutional architectures. Furthermore, the proposed method also aims to make the model explainable using explainability techniques, in this way we make diagnostic decisions transparent. The experimental analysis shows an accuracy of 0.8480, a precision of 0.8645, a recall of 0.8477, showing the effectiveness of the proposed method on eye disease detection. Full article