Search Results (1,099)

This work explores the application of Spiking Neural Networks (SNNs) and Continual Learning (CL) methodologies to the problem of steering angle regression, using autonomous driving simulation as the experimental context, with a focus on energy efficiency and alignment with sustainable computing objectives. The primary goal was to design and implement CL techniques in SNNs to assess the model’s ability to maintain accuracy in explored environments while reducing CO${}_2$ emissions through the optimized use of a subset of the data. This study emerges in response to the increasing energy demand of deep learning models, which poses a challenge to sustainability. SNNs, inspired by the efficiency of biological neural systems, offer significant advantages in terms of computational and energy consumption, making them a promising alternative. CL techniques, such as Elastic Weight Consolidation and replay memory, are integrated to mitigate catastrophic forgetting in sequential learning tasks. The methodology includes adapting the PilotNet architecture for SNNs, preprocessing datasets generated in the Udacity driving simulator, and evaluating models in incremental learning scenarios. The experiments compare the performance of SNNs with CL against baseline models without CL, using mean squared error (MSE), computational efficiency, and equivalent CO${}_2$ emissions as evaluation metrics. The results demonstrate that replay memory enables the retention of prior knowledge with a limited increase in energy consumption. This work concludes that SNNs with CL are a viable alternative for sustainable AI applications. Future research directions include a focus primarily on hardware-specific implementations and real-world testing. Full article

The skin–brain axis constitutes a complex, bidirectional network integrating cutaneous sensory, immune, and neuroendocrine systems with central neural circuits involved in emotion regulation, stress responsivity, and social cognition. Advances in psychodermatology and cosmetic science have progressively extended this framework to the emerging field of neurocosmetics, which explores how topical formulations, sensorial properties, and cutaneous neuromodulators may influence psychological well-being, affective states, and perceived stress. The aim of this narrative review is to synthesize current evidence on the biological foundations of the skin–brain axis and to critically examine the implications of these mechanisms for neurocosmetic interventions from a psychological and psychiatric perspective. It describes the biological substrates underlying skin–brain communication, including the cutaneous hypothalamic–pituitary–adrenal axis, neuropeptides, neurotrophins, transient receptor potential channels, and endocannabinoid signaling, and examines how these pathways are targeted by neurocosmetic interventions. Particular attention is devoted to neuroactive compounds, such as peptides, cannabinoids, botanicals, and aromatherapeutic molecules, as well as to sensorial strategies involving texture, temperature, and olfactory cues, which may modulate mood, anxiety, and self-perception through peripheral mechanisms. From a psychological and psychiatric perspective, the review discusses the intersection between stress-related skin conditions, body image disturbances, and emotional dysregulation, highlighting how cosmetic practices may influence subjective well-being beyond purely aesthetic outcomes. Methodological limitations of the existing literature, including the heterogeneity of study designs and outcome measures, as well as ethical considerations related to mood- and stress-related claims in cosmetic products, are critically examined. Finally, future research directions are outlined, and a translational framework is proposed to integrate dermatology, neuroscience, and mental health within next-generation cosmetic science. Full article

The escalating crisis of plastic pollution has positioned microplastics (MPs) as globally pervasive environmental contaminants, with a documented presence across aquatic, terrestrial, and atmospheric ecosystems, as well as within biological organisms. A growing body of evidence suggests that MPs not only threaten ecological integrity but may also induce multifaceted neurotoxic effects in humans, particularly targeting the functional architecture of the prefrontal cortex (PFC). As the central regulator of cognition, emotional processing, and behavioral control, PFC dysfunction has been hypothesized to be associated with cognitive deficits, emotional dysregulation, and behavioral abnormalities. In this comprehensive review, we synthesize the current understanding of MP-mediated neurotoxicity through three interconnected pathways: (1) structural and functional impairment of PFC neural networks, (2) disruption of neurotransmitter homeostasis, and (3) potential associations with neuropsychiatric pathogenesis. By integrating these mechanistic insights, this work aims to provide a scientific foundation for risk assessment frameworks and evidence-based environmental health policies. Full article

Structurally complex plasmonic nanoarchitectures represent an emerging class of nanomaterials with properties that extend beyond those of conventional spherical nanoparticles. Their distinctive structural motifs generate dense near field electromagnetic hot spots, expand interfacial surface area, and create biophysical environments at the nano–bio interface that can actively engage cellular signaling networks relevant to neural regeneration and aging. Despite growing interest in these platforms, a systematic, omics-guided synthesis that links nanoparticle structural features to transcriptomic programs and regenerative outcomes has been lacking. In this review, we summarize recent advances in high complexity plasmonic nanoparticle engineering and integrate published omics-based evidence of their cellular effects, organizing the discussion. Across these studies, transcriptomic analyses of nanoparticle treated neural systems consistently highlight three convergent biological themes: mitigation of oxidative stress and activation of antioxidant pathways, suppression of neuroinflammatory signaling, and induction of neuronal developmental and plasticity programs. Collectively, the omics-guided findings synthesized here suggest that structural complexity in plasmonic nanoarchitectures is not merely a synthetic achievement but a tunable determinant of cellular state, with important implications for the rational design of regenerative nanomedicines targeting neurodegenerative diseases and age-related neuronal decline. Full article

A physics-informed neural network (PINN) is developed to estimate the spatially varying parameters of the time-dependent heat equation in one dimension. The proposed model incorporates both the forward and inverse problems to estimate the temperature and thermal properties of a laser-induced interaction with biological tissue. The network can detect the presence and location of a second layer of tissue, if it exists, and estimate the thermal coefficients of each substance. This ability to model nonhomogeneous properties in tissue subjected to laser irradiation has many important applications in medical procedures. An ensemble method is used to quantify the epistemic uncertainty of all estimates to identify weaknesses in the model. Aleotoric uncertainty is simulated through noise perturbations, demonstrating robust estimates in the presence of measurement error. The uncertainty associated with parameter estimation provides insight into the ill-posedness of the inverse problem. Full article

Durian (Durio zibethinus Murray) is Thailand’s most economically significant fruit export, yet foliar diseases pose a major threat to productivity and crop quality. Early-stage symptoms of several durian leaf diseases are visually similar, making reliable diagnosis difficult for farmers and even trained agronomists. This study aims to develop and evaluate an automated deep learning-based system for durian leaf disease classification under realistic field conditions. A dataset of 6119 leaf images representing six classes—Leaf_Healthy, Leaf_Colletotrichum, Leaf_Algal, Leaf_Phomopsis, Leaf_Blight, and Leaf_Rhizoctonia—was compiled from public datasets and field-collected samples. Six convolutional neural network (CNN) architectures—ConvNeXt, ResNet, DenseNet201, InceptionV3, EfficientNet-B3, and MobileNetV3—were benchmarked using a unified transfer-learning training protocol. Class imbalance was addressed using weighted cross-entropy loss, and performance was evaluated on a stratified held-out test set using accuracy, precision, recall, and F1-score metrics. The results show that ConvNeXt achieved the highest performance with 98.00% accuracy and a weighted F1-score of 0.98, followed by ResNet (96.82%) and DenseNet201 (96.09%), while efficiency-oriented models plateaued near 91%. Confusion matrix analysis revealed consistent misclassification among visually similar disease categories—Leaf_Algal, Leaf_Blight, and Leaf_Phomopsis—indicating biological similarity in lesion appearance rather than model limitations. The best-performing model was deployed as a publicly accessible web application using Gradio, enabling real-time disease diagnosis with an average inference time of approximately 0.54 s per image. Unlike prior studies, this work combines large-scale architecture benchmarking, class imbalance mitigation, and real-world deployment within a single unified framework. These findings demonstrate that modern CNN architectures can provide highly accurate and scalable disease detection tools, supporting precision agriculture by enabling early diagnosis, reducing inappropriate pesticide use, and improving decision-making for durian farmers. Full article

Early detection is a key tool for mitigating the devastating effects of wildfires. Single-frame detection methods that do not consider inter-frame dependencies often fail to detect smoke plumes at the earliest stage and at greater distances, or produce excessive false alarms. Biological vision is particularly sensitive to motion cues, and this translates well to automated systems. Recent temporal-memory approaches have demonstrated improved performance over purely spatial methods, but typically rely on complex, computationally heavy multi-stage architectures. This study investigates the possibility of encoding temporal and contextual information into additional image channels as a basis for compiling data models with increased information content. Seven distinct data models were proposed, and corresponding datasets were generated to train standard YOLO architectures without modifications to the network structure. The datasets were compiled from real wildfire footage collected from an operational wildfire surveillance system in Croatia, comprising 333 annotated sequences of real fires recorded between 2018 and 2024. Experimental evaluation compared the performance of YOLO models trained on the information-enriched datasets with those trained on standard RGB images. Based on the results, the best data model for early wildfire smoke detection, combining original RGB channels with short-term and long-term temporal memory, was selected. Comparative evaluation demonstrated improved detection accuracy, achieving up to 5 percent higher true-positive detection rate for models trained on spatio-temporal data compared to standard RGB images, while maintaining low inference latency. The proposed approach shifts the focus to the structure and information content of the data while preserving the efficiency of standard convolutional neural network architectures. This approach could be applied to other problems requiring high efficiency and real-time operation, where temporal and contextual information can improve detection performance. Full article

This paper presents a unified analytical and computational framework for the study of typhoid fever transmission dynamics governed by a Caputo fractional-order compartmental model of order $\kappa \in (0,1]$. The population is stratified into five epidemiological classes, namely susceptible $\left(\mathcal{S}\right)$, asymptomatic $\left(\mathcal{A}\right)$, symptomatic $\left(\mathcal{I}\right)$, hospitalised $\left(\mathcal{H}\right)$, and recovered $\left(\mathcal{R}\right)$, and the governing system explicitly incorporates asymptomatic transmission, treatment dynamics, and temporary immunity with waning. The use of the Caputo fractional derivative is motivated by the well-documented existence of chronic asymptomatic Salmonella Typhi carriers, whose heavy-tailed sojourn times in the carrier state are naturally encoded by the Mittag–Leffler waiting-time distribution arising from the fractional operator. A complete qualitative analysis of the fractional system is carried out: the basic reproduction number ${\mathcal{R}}_0$ is derived via the next-generation matrix method; local and global asymptotic stability of both the disease-free equilibrium ${\mathcal{E}}_0$ (when ${\mathcal{R}}_0\le 1$) and the endemic equilibrium ${\mathcal{E}}^{*}$ (when ${\mathcal{R}}_0>1$) are established using fractional Lyapunov theory and the LaSalle invariance principle; and the normalised sensitivity indices of ${\mathcal{R}}_0$ are computed to identify transmission-amplifying and transmission-suppressing parameters. Existence, uniqueness, and Ulam–Hyers stability of solutions are established via Banach and Leray–Schauder fixed-point arguments. To complement the analytical results, a fractional physics-informed neural network ($\mathcal{PINN}$) framework is developed to simultaneously reconstruct compartmental trajectories and identify unknown biological parameters from sparse synthetic observations. $\mathcal{PINN}$ embeds the L1-Caputo discretisation directly into the training residuals and employs a four-stage Adam–L-BFGS optimisation strategy to recover five trainable parameters $\Theta$ = $\{\varphi ,\mu ,\sigma ,\psi ,\beta \}$ across three fractional orders $\kappa \in \{1.0,0.95,0.9\}$. The estimated parameters show strong agreement with the true values at the classical limit $\kappa =1.0$ ($\mathrm{MAPE}=2.27\%$), with the natural mortality rate $\mu$ recovered with $\mathrm{APE}\le 0.51\%$ and the transmission rate $\beta$ with $\mathrm{APE}\le 3.63\%$ across all fractional orders, confirming the structural identifiability of the model. Pairwise correlation analysis of the learned parameters establishes the absence of equifinality, validating that $\beta$ can be reliably included in the trainable set. Noise robustness experiments under Gaussian perturbations of $1\%$, $3\%$, and $5\%$ demonstrate graceful degradation ($\mathrm{MAPE}$: $0.82\%\to 3.10\%\to 7.31\%$), confirming the reliability of the proposed framework under realistic observational conditions. Full article

Background/Objectives: Carcinoembryonic antigen (CEA) is widely used in colon cancer management; however, its diagnostic and prognostic accuracy is limited by biological variability, as well as false-positive or false-negative results. Radiomics provides quantitative descriptors of tumor heterogeneity and offers objective assessment of tumor characteristics. This study aimed to evaluate the potential of computed tomography (CT)-based radiomic features to distinguish between CEA-positive and CEA-negative colon cancer patients. Methods: In this retrospective study, 150 patients with histopathologically confirmed colon cancer were screened, and 109 were eligible after image-quality assessment (53 CEA-positive, 56 CEA-negative). A total of 107 radiomic features were extracted from preoperative contrast-enhanced CT images. After z-score normalization, feature robustness was assessed using intra- and inter-observer agreement. Correlation-based feature selection (|ρ| ≥ 0.7) was applied. Five machine-learning classifiers—Support Vector Machine (SVM), Decision Tree, Ensemble, k-Nearest Neighbor (k-NN), and Neural Network (NN)—were trained using stratified 5-fold cross-validation. Performance was evaluated using accuracy, recall, specificity, F1-score, and ROC-AUC. Results: The best performance was obtained with 41 selected features. The k-NN classifier achieved the highest accuracy (77.4 ± 2%) and ROC-AUC (0.8523 ± 0.013), while SVM and NN achieved the highest recall (83.0 ± 0.3). These models showed balanced and robust performance in distinguishing CEA-positive from CEA-negative patients. Conclusions: CT-based radiomic analysis combined with machine learning—particularly k-NN, SVM, and neural network classifiers—showed promising performance in differentiating colon cancer patients according to serum CEA status. Radiomic features may provide imaging-based information associated with serum biomarkers such as CEA, potentially enhancing tumor characterization and supporting more personalized decision-making. Full article

Background: Standard spirometry fundamentally overlooks the mechanical dynamics of forced expiration. This study derived novel biomechanical parameters to establish functional phenotypes and predict clinical respiratory impairments. Methods: Utilizing 16,596 acceptable spirometry records from NHANES (2007 to 2012), parameters reflecting kinetic power, mass constraint, and airway instability were mathematically derived. Principal component analysis, K-means clustering, and a Multilayer Perceptron neural network were sequentially applied. Results: Three distinct biomechanical phenotypes emerged: Load-Constrained (45.4%), Mechanically Efficient (23.5%), and Dynamic Collapse (31.0%). Aging significantly degraded kinetic power, demonstrating a steeper functional decline in males (p < 0.001). The neural network achieved 93.2% testing accuracy in classifying spirometric abnormalities. Crucially, Dynamic Airway Collapse Ratio (100% normalized importance), BMI (89.4%), and kinetic power (86.2%) fundamentally outperformed traditional demographic predictors such as chronological age (20.4%) and biological sex (7.1%). Conclusions: Structural and dynamic kinetic factors drive pulmonary dysfunction far more accurately than conventional demographics. Classifying these mechanical phenotypes facilitates highly targeted precision cardiopulmonary rehabilitation. Full article

The microbiota–gut–brain axis (MGBA) is a complex bidirectional communication network integrating neural, endocrine, immune, and metabolic pathways linking intestinal microbiota to central nervous system function. Increasing evidence indicates that microbiota-derived signals are critical regulators of neurodevelopment and may contribute to vulnerability to neurodegenerative disorders across the lifespan. In this narrative review, we synthesize experimental and clinical evidence to define the key biological mechanisms underlying microbiota–brain interactions. Converging data indicate that immune activation, barrier dysfunction, and microbial metabolites, particularly short-chain fatty acids and tryptophan-derived compounds, represent central mediators linking gut dysbiosis to neuroinflammatory and neurodegenerative processes. Early-life microbial perturbations, driven by factors such as antibiotic exposure, diet, and psychosocial stress, appear to induce long-term immunometabolic programming that may increase susceptibility to neurological disorders later in life. Clinical studies consistently associate dysbiosis with neurodevelopmental conditions and major neurodegenerative diseases, including Alzheimer’s disease and Parkinson’s disease; however, causal relationships remain incompletely defined due to heterogeneity and the predominance of observational data. Overall, the available evidence supports a lifespan model in which microbiota-driven immune and metabolic dysregulation contributes to both early neurodevelopmental trajectories and late-life neurodegeneration. While microbiome-based biomarkers and therapeutic strategies show promise, their clinical translation requires validation in longitudinal and interventional studies. Full article

Background: Accurate identification of cancer driver genes is essential for understanding tumorigenesis and developing targeted therapies. Although graph neural networks (GNNs) have advanced multi-omics integration, existing methods often simply concatenate omics features and underutilize the topological information of biological networks. Methods: We propose M-GNN, a multi-modal GNN framework for cancer driver gene prediction. It employs separate Graph Convolutional Network (GCN) encoders to process four types of omics data (mutation, expression, methylation, copy number variation (CNV)), each represented as a 16-dimensional vector. We incorporate knowledge distillation by using soft labels from a pre-trained teacher model to enhance feature representation. An attention mechanism adaptively fuses the encoded omics features, and a dual-path classifier combining a GCN and a Multilayer Perceptron (MLP) preserves both intrinsic gene properties and network topology. Results: Experiments on three public protein–protein interaction (PPI) networks show that M-GNN consistently achieves the highest or second-highest AUPRC compared to five state-of-the-art methods. Ablation studies confirm the contribution of each module, and biological interpretability analysis—including analysis of GO enrichment and drug sensitivity—validates the reliability of the predicted genes. Conclusions: M-GNN provides a robust and interpretable computational tool for systematic cancer driver gene identification, effectively integrating multi-omics and network data. Full article

The von Neumann architecture faces a “memory wall” problem due to the physical separation of memory and processor, posing major challenges to energy efficiency and latency in the era of artificial intelligence. To overcome these bottlenecks, artificial synaptic devices inspired by biological systems have emerged as an important research direction. By integrating sensing and computing functions at the device level, these architectures provide a promising approach for the efficient processing of natural physical signals. Supported by advances in functional materials and artificial neural network (ANN) algorithms, artificial synaptic devices are capable of perceiving and processing various external stimuli, showing strong potential for applications in intelligent electronic skins, robotics, and edge computing. This review provides a comprehensive overview of recent advances in artificial synaptic devices, with particular emphasis on tactile and visual sensing applications. We discuss representative device types and operating mechanisms, analyze critical challenges from the perspectives of material engineering and functional integration, and further summarize potential solutions and future trends toward multimodal sensory–memory–computing systems. Full article

Glucocorticoid-induced hypertension affects over 30% of treated patients, yet its underlying mechanisms remain unclear, particularly how glucocorticoids regulate renin within the renin-angiotensin-aldosterone system (RAAS). Modeling these dynamics is difficult because only four dose-response measurements are available at a single 24-h timepoint (36 observations total), while the system depends on roughly eleven biochemical parameters spanning minutes-long receptor interactions to days-long protein secretion. Classical parameter estimation becomes unreliable in this extremely underdetermined setting, and purely data-driven methods offer limited biological interpretability. In this paper, we introduce a physics-informed neural network (PINN) framework that integrates ELISA measurements from As4.1 juxtaglomerular cells, ordinary differential equations describing glucocorticoid receptor signaling and renin transcription, and automatic differentiation to enforce mechanistic constraints. By systematically tuning synthetic-data weights (SW in {0.2, 0.3, 0.5}), we identify an intermediate value of SW = 0.3 that provides the best overall balance between predictive accuracy, accepted ensemble size, and biologically plausible parameter estimates among the tested configurations. The framework uses adaptive constraint scheduling with a plateau ramp to reduce premature convergence and introduces calibrated plausibility thresholds reflecting experimental noise. The accepted PINN ensemble (n = 5, 50% success rate) achieved R² = 0.803, compared with 0.759 for the SW = 0.5 baseline and −0.220 for the ODE-only baseline, with RMSE = 0.024. Key learned parameters (IC₅₀ = 2.925 ± 0.012 mg/dL, Hill = 1.950 ± 0.009) are biologically plausible within the model assumptions, and the best single accepted model attained R² = 0.891. Information criteria favored the PINN over the ODE model, with improvements of approximately 77× (AIC) and 5.9× (BIC). Despite training on a single timepoint, the PINN also infers full 48-h trajectories and reproduces non-monotonic dose-response behavior. This work presents, to our knowledge, the first PINN framework for glucocorticoid-mediated renin regulation and should be interpreted as a proof-of-concept approach for integrating sparse biomedical data with mechanistic constraints. The inferred parameters and temporal dynamics are best viewed as model-dependent, hypothesis-generating estimates rather than validated biological quantities. Full article

Despite the success of artificial neural networks in solving numerous tasks, they face significant challenges, including difficulties in online adaptation and rapidly increasing energy consumption. As a biologically plausible alternative, spiking neural networks offer promising capabilities for efficient cognitive computing. Recently, a three-element spiking neuron model consisting of a threshold selector, a tunnel diode, and a capacitor was proposed. In this work, we experimentally validate this model using a threshold selector hardware emulator and demonstrate its dynamical equivalence to the biologically plausible Izhikevich neuron model. To evaluate the novel neuron’s applicability for cognitive computing, we implement a liquid state machine (LSM) reservoir architecture with spatially dependent random topology for synaptic weight distribution. Our simulations on the MNIST and Fashion-MNIST benchmarks demonstrate competitive classification accuracy (97.9% and 89.5%, respectively) while offering estimated energy efficiency and processing speed enhancements compared to existing FPGA-based and memristor-based spiking reservoir implementations. The developed reservoir is feasible for processing neuromorphic sensors output, including visual perception tasks. Full article