Search Results (468)

The proliferation of Edge-AI in personalized healthcare has driven significant demand for energy-efficient Systems-on-Chip (SoCs) capable of executing high-accuracy, real-time disease detection. Conventional accelerator architectures struggle to simultaneously accommodate disparate AI models. Specifically, memory-intensive Convolutional Neural Networks (CNNs) for high-fidelity feature extraction and event-driven Spiking Neural Networks (SNNs) for ultra-low-power, brain-inspired computation. To address this bottleneck, this paper presents a comprehensive survey of Reconfigurable Hybrid Neural Networks (RHNNs), an emerging paradigm that dynamically merges the strengths of CNNs and SNNs to meet the stringent resource constraints of biomedical edge devices. We establish a comprehensive taxonomy of existing RHNN architectures, categorizing them by hardware interconnection topologies, dataflow orchestration strategies, and internal structural adaptation mechanisms. Furthermore, we examine the integration of these hybrid accelerators within the open-source RISC-V processor ecosystem, evaluating how custom instruction set extensions optimize control efficiency and minimize energy overhead. The survey also analyzes commonly used datasets based on three major biomedical signal modalities, including electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG), in the context of processing systems for hardware accelerators. Finally, we highlight the open research challenges and outline future research directions to guide the development of next-generation biomedical intelligent systems. Full article

Drug delivery systems based on nanoparticles have emerged as promising approaches for overcoming the blood–brain barrier (BBB), a major obstacle to treating disorders of the central nervous system (CNS). There are several reasons why conventional therapies fail, including poor brain penetration, rapid drug clearance, and nonspecific distribution. This review critically evaluates recent advances in nanoparticle-mediated BBB targeting, focusing particularly on in vivo findings. As part of this review, lipid-based, polymeric, metallic, dendrimeric, exosome-inspired, and magnetic nanoparticles are discussed in conjunction with their transport mechanisms. The review compares their therapeutic efficacy, biodistribution, targeting ability, and safety across a variety of neurological conditions. Additionally, emerging technologies are discussed, including biomimetic nanoparticles, stimuli-responsive systems, artificial intelligence, and personalized nanomedicine. Additionally, this review critically discusses the major barriers to clinical translation, including biosafety, manufacturing, and regulatory challenges. As a result, this review provides an updated perspective on current progress and future prospects for developing effective brain-targeted nanomedicine. Full article

Autism spectrum disorder (ASD) and epilepsy are complex, frequently co-occurring neurodevelopmental and neurological disorders that share key mechanisms, such as altered neurotransmission, oxidative stress, neuroinflammation, and gut–brain axis disruption. Despite pharmacological advances, current treatments often provide only partial relief and are associated with significant side effects. The comorbidity of ASD and epilepsy, affecting millions worldwide, remains under-recognised and poorly addressed, imposing a profound burden on patients, families, and healthcare systems through reduced quality of life, increased caregiving demands, and substantial social and economic costs. This review highlights the convergent pathways shared between ASD and epilepsy, including immune dysregulation, synaptic dysfunction, and metabolic imbalance, which create opportunities for unified therapeutic strategies. Marine algae have emerged as a sustainable source of bioactive compounds offering a unique potential to address these overlapping pathologies. Algal polyunsaturated fatty acids, carotenoids, polyphenols, polysaccharides, and vitamins have antioxidant, anti-inflammatory, neuroprotective, and microbiota-modulating activities. By addressing both the biological underpinnings and clinical burden of ASD–epilepsy comorbidity, algae-based strategies represent a novel and ecologically sustainable direction for mitigating ASD–epilepsy comorbidity and advancing marine-inspired neurotherapeutics. 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

The neural circuits of the human brain are highly complex (due to the number of neurons and the diversity of synaptic connections), hindering the analysis of the pathological mechanisms of neurodegenerative diseases. Invertebrates with simple yet well-differentiated nervous systems have a natural advantage over mammalian model organisms in the identification of pathogenic genes and functional studies of neurodegenerative diseases. They can provide unique and profound insights into the pathogenesis of complex human neurodegenerative diseases and the formulation of intervention strategies. This article reviews the conserved mechanisms of three neurodegenerative diseases across species, including protein homeostasis imbalance and aggregation toxicity, mitochondrial dysfunction and metabolic abnormalities, axonal transport defects, and loss of synaptic function. Based on research on three invertebrates in the field of neurodegeneration, namely Caenorhabditis elegans (C. elegans), Drosophila melanogaster (D. melanogaster), and Bombyx mori (B. mori), we cover three major types of neurodegenerative diseases: Alzheimer’s disease (AD), Parkinson’s disease (PD), and Huntington’s disease (HD). The aim is to find important inspirations for the future prevention and treatment of neurodegenerative diseases from the aspects of the material basis and existing treatment strategies. Full article

A Spiking Neural Network (SNN) is a kind of brain-inspired and event-driven network, which is becoming a promising energy-efficient alternative to Artificial Neural Networks (ANNs). In recent years, SNN methods have been successfully applied in the fields of electromagnetic signal processing and image signal processing, particularly in application scenarios that require low energy consumption. However, the performance of SNNs by direct training is far from satisfactory. In this paper, we study a novel learning method named SAD-SNN (Spatial-Activation Distillation for Spiking Neural Networks), which utilizes the ANN model to guide the SNN model learning. Unlike prior works that rely on element-wise feature alignment approaches, SAD-SNN aligns spatial-activation maps at different resolutions of the teacher and student networks. Specifically, we introduce a direct alignment approach, which defines a spatial-activation loss and normalizes the representation vectors of ANN and SNN, to alleviate the unexpected precision loss. This enables the knowledge of teacher ANNs to be effectively transferred to train student SNNs. On three image classification datasets, our proposed SAD-SNN outperforms other SNN training methods no matter whether homogeneous or heterogeneous teacher ANNs are used. Furthermore, we apply SAD-SNN to the electromagnetic signal detection task, demonstrating strong generalization ability and superior performance. In conclusion, the experimental results on various tasks and SNN architectures demonstrate that our method is a general and effective solution that significantly improves the learning of student SNNs with only two time steps. Full article

Recent advances in biologically inspired neural computation have sparked increasing interest in developing hardware-efficient architectures capable of emulating brain-like cognitive abilities like low power consumption and less inference latency. However, significant hardware overhead and spike-processing complexity remain major challenges in FPGA implementations of spiking neural networks. In this work, we propose a sparse spike-aware and weight pruning FPGA architecture based on LIF neurons that minimizes spike activity and synaptic operations through pruning-aware event-driven computation. The proposed sparse spike-aware SNN architecture was evaluated using the Iris dataset. The dataset was divided into 80% training and 20% testing samples. Pre-trained weights obtained from software-level training were deployed onto the FPGA-based LIF classifier. Classification accuracy was computed by comparing predicted output spikes against ground-truth class labels. Experimental results demonstrated that the proposed architecture achieved an overall classification accuracy of 93.3% while maintaining low hardware resource utilization and reduced power consumption. Moreover, the implementation achieves superior energy efficiency, consuming only 3.5 W total on-chip power and utilizing 587 logic cells, confirming its suitability for compact, real-time edge computing neuromorphic applications. Full article

Familiar and unfamiliar face recognition is an important cognitive process with potential applications in brain-computer interface (BCI) systems and neurocognitive assessment. Classification of familiar and unfamiliar faces based on electroencephalography (EEG) remains challenging because discriminative information is distributed across multiple frequency bands, temporal windows, and scalp channels. This study proposes LEPST-RBFNet, which combines a Learnable Entropy-Power Scaling Transform (LEPST) and a radial basis function (RBF) network for EEG-based familiar and unfamiliar face classification. The model first segments the EEG into multi-scale time-frequency segments and then extracts local standard-deviation features. After that, a learnable entropy-power-inspired scaling transformation is applied using the LEPST module to obtain adaptive local time-frequency EEG entropy features. The transformed features are classified by an RBF prototype module with learnable centers and an adaptive kernel-width parameter. Experiments using a five-fold leave-one-block-out validation protocol show that LEPST-RBFNet achieves a superior average classification accuracy of 73.60%. Ablation and visualization analyses further indicate that the proposed model provides a competitive and interpretable framework for EEG-based familiar and unfamiliar face recognition. Full article

The von Neumann architecture, due to the physical separation between memory and processor, has limited the development of data-intensive applications. Neuromorphic computing technologies inspired by the brain’s parallel and event-driven operation mechanisms have enabled low-power in-memory computing. Memristors with tunable conductance can emulate biological synapses, while flexible memristors further offer mechanical flexibility, making them suitable for wearable electronics and intelligent sensing systems. This review systematically summarizes the switching mechanisms of flexible neuromorphic memristors, including conductive filaments, interface effects, ferroelectricity, phase change, and multiple synergistic mechanisms. It categorically discusses natural and bio-derived materials, synthetic organic/polymer materials, and inorganic functional materials, and introduces strategies for enhancing flexibility. The article also covers device architectures such as sandwich structures, crossbar arrays, and fiber-based textile structures, along with low-temperature fabrication techniques. Finally, it reviews recent advances in neuromorphic computing, in-memory computing, biomimetic sensing, and biomedical wearable systems. Challenges related to mechanical stability and device uniformity are analyzed, and future directions toward self-healing materials and integrated sensing-storage-computing systems are outlined. This comprehensive review bridges the gap between material innovation and system-level integration in flexible neuromorphic memristors, providing a valuable roadmap for accelerating the development of next-generation wearable artificial intelligence, edge computing, and bio-integrated electronic technologies. Full article

Mechanistic simulation and machine learning are powerful but complementary tools: physics-based simulation is interpretable yet computationally expensive and blind to real-world context, whereas machine learning is fast but data-hungry and opaque. Biological systems resolve this tension elegantly, coupling physically grounded mechanoreceptor sensing with higher-level neural interpretation that places those signals in context. Inspired by this layered architecture, we present Mechanics-AI, an open-source framework that mirrors the same sensing-then-interpretation logic computationally. A first learning layer (ML1) emulates expensive finite-element, computational fluid dynamics and multiphysics simulations to produce interpretable physical metrics such as stress, strain, shear, and thermal and moisture fields, while a second layer (ML2) fuses these metrics with heterogeneous real-world metadata to predict categorical outcomes and design recommendations. Eight algorithms are benchmarked automatically, the most accurate is selected for each task, and Shapley additive explanations expose the dominant physical drivers to preserve interpretability. The framework is demonstrated across three independent domains using a single unchanged pipeline: forensic traumatic brain injury prediction, optimisation of a bio-inspired humanoid bioreactor for tissue engineering, and a zero-emission building (ZEBAI) framework that couples thermo-hygro-mechanical simulation with Sobol-sampled surrogate modelling to design sustainable, low-carbon envelopes from recycled aggregate concrete by balancing structural safety, energy and embodied carbon. Despite entirely different physics, data and objectives, the same architecture generalises across all three, showing that bio-inspired, layered coupling of mechanistic simulation and contextual learning offers a reusable, interpretable route to cross-domain engineering prediction and sustainable design. Full article

Humans possess unique advantages in dealing with few-shot visual recognition scenarios, inspiring the development of meta-learning methods aimed at emulating these abilities. Current mainstream meta-learning primarily utilizes the monocular vision or the dual asymmetric complementary architectures, collectively referred to as Machine-visual Meta-Learning (MvML). Nevertheless, research has not yet developed an architecture for simulating the human binocular visual system, named Humanoid-visual Meta-Learning (HvML). This paper innovatively proposes an excellent paradigm BPIAL belonging to the HvML: Binocular Perception Instance Authentication Learning, which can alleviate the monocular shallowness and dual-branch processing instability of MvML. Structurally, our BPIAL comprises two interconnected binocular perception and information processing modules: BSEM and IAPM. The former module can simulate binocular visual field extraction, feature extraction and compression, and channel dimension reduction, while IAPM can simulate the logic, reasoning, and judgment processes of the two human visual branches and the brain. We have demonstrated the feasibility and correctness of BPIAL on five benchmarks. Sufficient and comparative experiments with the state-of-the-art methods have proved its superiority and effectiveness. Full article

Alzheimer’s disease remains one of the hardest disorders to drug, and most computational pipelines still tackle one target at a time and ignore brain penetration until late. We bring all of that into a single optimization problem. Our framework, called CAGE-QMol(Constraint-Aware Quantum-inspired Molecular optimization), turns the search for a brain-penetrant, dual BACE1/AChE inhibitor into a constrained quadratic unconstrained binary optimization (QUBO) and solves it with an ensemble of classical, quantum-inspired, and Quantum Approximate Optimization Algorithm (QAOA) backends. The pipeline begins with three real public datasets—MoleculeNet BACE, ChEMBL CHEMBL4822 (BACE1) and CHEMBL220 (AChE), and the TDC BBB_Martins blood–brain-barrier set—which together yield 12,465 unique molecules with at least one measured endpoint. Multi-task ExtraTrees predictors trained on Morgan ECFP4 fingerprints and physicochemical descriptors deliver scaffold-split test-set metrics of $R^2=0.624$ ($\mathrm{MAE}=0.587$) for BACE1 and $R^2=0.383$ ($\mathrm{MAE}=0.793$) for AChE. The optimizer combines these predictions with a Lipinski-based feasibility cone, a TDC-derived BBB classifier, and similarity-driven diversity into a constrained QUBO. We adapt the classical exact-penalty rule, $\lambda >{\Delta }_S/{\delta }_g$, which guarantees every global minimizer of the penalized energy is feasible, and specialize it so that the multiplier is computed from the data rather than hand-tuned. A 10-qubit PennyLane QAOA circuit is benchmarked against exact enumeration, simulated annealing, genetic search, Bayesian TPE, and random search across ten seeds; the QUBO formulation lets a genetic solver match the exact ground state on every seed, while ablations show that removing the QUBO selection collapses the mean therapeutic score from 6.242 to 5.976 ($p<{10}^{-3}$, paired t-test). Top-50 candidates exhibit a mean BBB probability of 0.716, a mean QED of 0.768, and 100% Lipinski feasibility, with leading scaffolds (tetrahydroisoquinolinone, methoxy-tetrahydronaphthalene-urea, indanone-piperidine) reproducing motifs found in published dual BACE1/AChE inhibitor families. This paper contributes (i) a mathematically grounded penalty selection rule for constrained drug-discovery QUBOs, (ii) a single end-to-end pipeline from raw public data to ranked, 3D-embedded leads, and (iii) reproducible head-to-head benchmarks between classical, quantum-inspired, and QAOA-simulated optimizers on a real Alzheimer’s task. Full article

The topology of spiking neural networks (SNNs) plays an important role in determining their dynamic representation ability, recognition performance, and biological interpretability in speech recognition. However, most existing SNN reservoirs are constructed using random, regular, or manually designed connectivity patterns, which may not reflect the functional organization of the human brain during speech perception. In this study, we propose a task-state fMRI-constrained SNN framework for speech recognition. Human fMRI data acquired during naturalistic English audiobook listening are used offline to derive a task-state whole-brain functional topology, which serves as a biologically inspired structural prior for the recurrent connectivity of the SNN reservoir. Because the fMRI and downstream isolated-digit recognition tasks use different speech paradigms, this topology is interpreted as a general speech-listening prior rather than a digit-specific neural representation. The Schaefer-400 cortical parcellation is used to define 400 whole-brain functional nodes, all of which are retained to preserve distributed cortical interactions during speech listening. Within this topology, 7 SomMotB_Aud parcels are identified as auditory core nodes and analyzed as an embedded auditory circuit. Compared with resting-state fMRI, task-state fMRI shows enhanced functional connectivity among these auditory nodes, indicating task-related auditory-circuit activation. The resulting 400-node task-state topology is mapped onto the recurrent connectivity of the SNN reservoir. This mapping is regarded as a topology-constrained computational abstraction rather than a direct model of biological information transmission. During recognition, speech spike trains are the only external input, while fMRI data are used only for offline topology construction. Experimental comparisons with baseline SNNs show that the proposed topology improves recognition performance and biological interpretability. Resting-state topology comparison, auditory-core contribution analysis, threshold-sensitivity analysis, and statistical testing are further used to evaluate robustness. These findings suggest that speech-evoked whole-brain functional organization may provide an effective topology prior for biologically inspired speech recognition models. Full article

Fixed-bottom or floating offshore structures are the foundations, platforms, and associated infrastructure that allow for oil and gas production systems, offshore wind turbines, and cabling. The remote nature of these structures and the harsh environment with high variability in wind, waves, currents, and weather make construction activity very difficult and unpredictable; the cost of variation in the schedule can lead to high construction vessel and personnel costs. The adoption of artificial intelligence using trends observed in historical data can help achieve more accurate construction costs and schedule predictions, reducing the capital expenditure cost of installation. A resource-significant activity, sometimes called a resource-critical activity or high-resource-demand activity, is an activity on a construction or project schedule that consumes a disproportionately large share of one or more resources compared with others. Plant Design Modelling (PDM) is a digital process that creates and manages a detailed 3D model of a building’s physical and functional characteristics and semantic information, such as cost and schedule. PDM serves as a single source of truth for multidisciplinary activities and, therefore, serves as a rich data source for various construction applications, including project scheduling and cost estimation. Neural networks (NNs), a subset of machine learning algorithms inspired by the human brain, excel at identifying patterns in complex datasets and making predictions, such as forecasting costs based on non-linear relationships and historical trends. Data from an offshore structure modification project were extracted from Aveva’s Everything PDM, focusing on installation activities to create a dataset for machine learning model training. The structured data extracted exhibit non-linear patterns; therefore, linear, regularised linear, robust linear, and the ensemble (tree-based) models and supervised neural network models with varied architecture and hyperparameter values were evaluated and compared. The best performance was obtained using the deep-optimised ANN model. The result obtained is consistent with previous studies. The neural network models show a superior ability to predict the non-linear nature of offshore construction activities’ time. Full article

Achieving rapid and accurate obstacle avoidance in complex and dynamic environments remains a significant challenge for robots. To enhance the adaptability and flexibility of humanoid arms for obstacle avoidance, a brain-inspired multi-pathway motion decision-making method is proposed to modulate rational planning and habitual actions of humanoid arms. Firstly, a novel framework integrating both a slow and a fast pathway is designed for motion decision-making tasks. Imitating the rational planning function of the prefrontal cortex, the slow pathway employs an improved planning approach based on Real-Time Rapidly exploring Random Tree Star (RT-RRT^*) to execute deliberate decisions, along with an improvement in planning via the Smart technique and the high-efficiency neighbor searching method. Meanwhile, mimicking the habitual responses governed by the striatum, the fast pathway utilizes an action model trained by Soft Actor-Critic to make quick and habitual motions. The model in the fast pathway is also used to guide the sampling strategy in the slow pathway. Moreover, to facilitate the integration and smooth transition between the two pathways, an emotional neural network is designed as the modulation module with inspiration from the structure and function of the amygdala. Based on body and obstacle information, the network generates emotional signals to modulate the involvement degree of the two pathways before each decision-making process. Experimental results demonstrate that the proposed multi-pathway framework achieves a higher obstacle-avoidance success rate than existing methods while generating motion characteristics that are consistent with certain aspects of human obstacle-avoidance behavior. Full article