工程技术最新文献

Parkinson's disease (PD) is among the two most prevalent neurodegenerative disorders (NDDs), affecting about 2-3% of individuals aged 65 and older. This NDD exhibits characteristic motor symptoms and several other non-motor features. Vocal deficits have been identified as one of the earliest quantifiable indicators of PD, which makes speech evaluation a viable, painless diagnostic instrument. We aim to apply machine learning (ML) models to vocal biomarkers for the early detection of PD, and use explainable artificial intelligence (XAI) techniques to interpret the predictions. The dataset is from Kaggle, a publicly reputable database, containing 1000 Parkinson's samples and 24 acoustic variables. We performed feature selection to identify the crucial vocal biological markers. Multiple machine learning (ML) models: Adaptive Boosting (AdaBoost), Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), LightGBM (LGBM), CatBoost, Gradient Boosting (GB), Histogram-Based Gradient Boosting (HGB), and K-Nearest Neighbors (KNN) were employed. We also used SHAP (Shapley Additive exPlanations), LIME (Local Interpretable Model-agnostic Explanations), and Partial Dependence Plot (PDP) to explain the model performances. The HGB model ranked highest (1.00) based on accuracy, precision, recall, and F1-score, respectively. Also, the Confidence intervals (CI) (1.00,1.00) and p-value of < 0.001 of HGB were computed. XAI showed that jitter and shimmer-based biomarkers were the strongest contributors to the prediction of PD. In this study, the results showed that vocal base biomarker screening is not only economical but also an accessible diagnostic tool. In subsequent studies, we hope to include more varied datasets to improve both model and therapeutic relevance.

Graphical abstract:

This research employs an integrated approach combining network pharmacology and molecular docking to assess the therapeutic potential of a Heat-Clearing and Dampness-Eliminating Formula alongside gut microbiota (GM) metabolites in the management of Behçet's disease (BD). Active constituents of the formula and GM-derived metabolites were sourced from specialized databases including TCMSP, SwissTargetPrediction, PubChem, and gutMGene. Disease-associated targets for BD and metabolite-related targets were compiled using publicly available datasets. Through protein-protein interaction (PPI) network construction and KEGG enrichment analysis, pivotal targets and major signalling pathways implicated in BD pathology were identified. Molecular docking simulations further assessed the binding interactions between active metabolites and target proteins, corroborating the predictions derived from network pharmacology. Further experimental validation using in vitro and in vivo models is warranted to substantiate these computational insights.

Coriandrum sativum L. (coriander) is a medicinal herb with diverse pharmacological properties, but its molecular mechanism in clear cell renal cell carcinoma (ccRCC) remains unclear. This study aimed to systematically investigate the underlying mechanisms of coriander in ccRCC by multi-omics analysis. Active compounds were screened using Traditional Chinese Medicine Systems Pharmacology (TCMSP) and predicted targets identified via SwissTargetPrediction (STP) and Similarity ensemble approach (SEA). Transcriptomic data from GSE53757 were analysed with WGCNA and intersected with coriander targets. Key genes were selected using LASSO, SVM, and random forest models. NEK6 was further analysed for clinical relevance, methylation, immune association, single-cell expression, molecular docking and molecular dynamics simulation. Fourteen coriander compounds were identified, yielding 22 potential ccRCC-related targets. NEK6 and PYGL were consistently selected by all machine learning algorithms. NEK6 was overexpressed in ccRCC and associated with better prognosis, promoter hypomethylation, and lower mutation rates. NEK6 expression correlated with immune infiltration, particularly macrophages, and was enriched in tumour and myeloid cells at the single-cell level. Molecular docking and molecular dynamics simulation revealed strong and stable binding of luteolin, quercetin, and chryseriol to NEK6. NEK6 may function as a prognostic and immune-regulatory biomarker in ccRCC. Coriander flavonoids could target NEK6 to modulate the immune microenvironment, providing new insight into plant-based therapeutic strategies for ccRCC.

Modern AI systems excel at pattern recognition and task execution, but they often fall short of replicating the layered, self-referential structure of human thought that unfolds over time. In this paper, we present a mathematically grounded and conceptually simple framework based on smoothed step functions-sigmoid approximations of Heaviside functions-to model the recursive development of mental activity. Each cognitive layer becomes active at a specific temporal threshold, with the abruptness or gradualness of activation governed by an impressiveness parameter [Formula: see text], which we interpret as a measure of emotional salience or situational impact. Small values of [Formula: see text] represent intense or traumatic experiences, producing sharp and impulsive responses, while large values correspond to persistent background stress, yielding slow but sustained cognitive activation. We formulate the recursive dynamics of these cognitive layers and demonstrate how they give rise to layered cognition, time-based attention, and adaptive memory reinforcement. Unlike conventional memory models, our approach captures thoughts and recall events through a recursive, impressiveness-sensitive pathway, leading to context-dependent memory traces. This recursive structure offers a new perspective on how awareness and memory evolve over time, and provides a promising foundation for designing artificial systems capable of simulating recursive, temporally grounded consciousness.

In biological neurons, synapses receive external stimuli to induce firing patterns. While the rapid generation of synapses regulates neural activity. In this paper, we use a magnetic-flux controlled memristor (MFCM) as a synapse to connect two functional neurons, establish the new coupled neurons, and study the synchronization characteristics. Firstly, we connect two neurons using memristive synapses, and derive the equations of the coupled neurons based on Kirchhoff's voltage law. Furthermore, we calculate the energy of the memristive coupling channels, and obtain the energy difference between the coupled neurons. Secondly, we propose a criterion for exponential growth controlled by energy difference. By setting higher coupling channel strength to establish synaptic connections, energy pumping can be effectively activated. Finally, for three modes, we analyze the energy evolution under the variations of memristive synapses, and find that the coupling channels are adaptively controlled by energy difference. The results show that when the coupling strength through synapses is enhanced, identical neurons can achieve complete synchronization, and different neurons can achieve phase locking. This study clarifies the underlying mechanisms of regulating coupled neurons via memristive synapses and explores how neurons achieve potential energy balance from the perspective of physical fields.

This paper designs two improved passive cosine-type ideal memristors and incorporates them into the Hopfield neural network, thereby proposing a novel cosine-type memristor-driven Hopfield neural network (CMDHNN). The model exhibits a planar equilibrium set and demonstrates extreme multistability, characterized by the coexistence of infinitely many attractors. The boundedness of the system is rigorously proven using the Lyapunov method. Nonlinear dynamics analysis tools, including bifurcation diagrams, Lyapunov exponent spectra, phase portraits, and time series plots, are employed to thoroughly investigate the model's complex chaotic dynamics. Leveraging the chaotic system of the proposed CMDHNN, an image encryption scheme is developed, in which chaotic sequences are utilized to generate diffusion and permutation key streams for encrypting the plaintext image. The results indicate that the encryption scheme based on this model exhibits excellent robustness and can effectively resist various common attacks.

Functional differentiation in the brain emerges as distinct regions specialize and is key to understanding brain function as a complex system. Previous research has modeled this process using artificial neural networks with specific constraints. Here, we propose a novel approach that induces functional differentiation in recurrent neural networks by minimizing mutual information between neural subgroups via mutual information neural estimation. We apply our method to a 2-bit working memory task and a chaotic signal separation task involving Lorenz and Rössler time series. Analysis of network performance, correlation patterns, and weight matrices reveals that mutual information minimization yields high task performance alongside clear functional modularity and moderate structural modularity. Importantly, our results show that functional differentiation, which is measured through correlation structures, emerges earlier than structural modularity defined by synaptic weights. This suggests that functional specialization precedes and probably drives structural reorganization within developing neural networks. Our findings provide new insights into how information-theoretic principles may govern the emergence of specialized functions and modular structures during artificial and biological brain development.

Plant genetic engineering represents an important aspect of modern agriculture, and new genetically modified (GM) crop varieties are entering the market on a regular basis. This necessitates the development of high throughput multi-target analytical methods to detect and quantify their presence for regulatory compliance. In this study, we present a multiplex dPCR method for discriminative quantification of 19 GM soybean events and the lectin (Le1) endogene on a nanowell plate-based all-in-one dPCR system. The method consists of four 5-plex assays, taking advantage of the platform's multiple fluorescence detection channels. The assays complied with the minimum performance requirements in terms of specificity, trueness, precision, sensitivity and dynamic range, making them suitable for use in routine detection and quantification of GM crops. This method represents the most comprehensive multi-target GM soybean quantification approach to date without the need for prior screening and features a simplified workflow, making it suitable for widespread adoption. Our study sets a precedent for rapid and straightforward development of multiplex dPCR GM crop quantification assays to address the evolving demands of regulatory monitoring.

Sleep staging is a critical indicator for assessing sleep quality and sleep disorders. Although significant progress has been made in sleep staging research, the representation of prominent waveforms and the capture of dynamic transitions between sleep stages still pose challenges. To address these issues, we propose MCTSleepNet, an Sleep staging Network containing Multiscale waveform representation, Composite attention and Time dependency learning modules based on single-channel electroencephalography (EEG). Firstly, multiscale waveform representation is learned from EEG signals using a dual-scale convolutional neural network (CNN). Then, a Composite Attention module is employed to enhance signal feature representation by considering both local and global contextual dependencies, thereby more effectively capturing prominent waveform features. Finally, a Bidirectional Gated Recurrent Unit (Bi-GRU) is used to learn the time dependent feature between EEG signals, enabling MCTSleepNet to model dynamic transitions between different sleep stages. Furthermore, considering the data imbalance between different sleep stages, this paper introduces an adaptive cross-entropy polynomial loss function to adjust the weights of different classes, thereby enhancing the model's attention to minority classes. Evaluation results on the publicly available Sleep-EDF-20 and Sleep-EDF-78 datasets demonstrate that MCTSleepNet performs exceptionally well in the sleep staging task.

Fast-spiking basket cells (FSBCs) govern hippocampal oscillations through their rapid and sustained firing patterns, which drive rhythmic inhibition onto postsynaptic neurons, thereby enforcing population synchrony in the gamma and other frequency bands that support cognitive processes. Despite the established role of FSBCs in hippocampal oscillations, the precise mechanisms by which their dendrites influence membrane potential responses across different frequency bands remain unclear. In this study, we simulate oscillation-like input protocols to explore how dendrites modulate the spectral responses of the membrane potentials of FSBCs. Our results show that FSBCs exhibit both slow and fast oscillatory components, which are shaped by their action potentials. Input synchrony is essential for determining both the fast-band response frequency and its coupling with the slow frequency, while the neuron's intrinsic firing dynamics maintain the stability of the fast-band peak frequency across theta-range inputs. Although dendritic Na[Formula: see text]/A-type K[Formula: see text] channel blockade and cp-AMPA enhancement both increase fast-band frequency, they differentially affect phase-amplitude coupling, with blockade reducing and cp-AMPA enhancement increasing it, highlighting the role of intrinsic dendritic conductances and cp-AMPA inputs in promoting coupling. Furthermore, we show that the spatial distribution of synaptic inputs along dendrites affects the response frequencies, with distinct frequencies observed at different dendritic locations according to their electrotonic distance. These findings provide insights into how the intrinsic properties of FSBCs influence their response to oscillatory inputs.

Supplementary information: The online version contains supplementary material available at 10.1007/s11571-026-10418-2.