搜索结果：Perceptron

Exacerbations, impaired health-related quality of life (HRQoL) and reduced exercise capacity increase the risk of hospitalisations and death in chronic obstructive pulmonary disease (COPD). However, their monitoring relies on in-person assessments, potentially delaying early care. While smart sensing technologies can enable remote monitoring, their use in predicting disease worsening remains limited. The TOLIFE Clinical Study A (CSA) aims to develop an artificial intelligence (AI) model integrating clinical data with smart sensing devices data to predict exacerbation onset and changes in HRQoL, dyspnoea and exercise capacity in people with COPD. TOLIFE CSA is a longitudinal observational study that will recruit 150 clinically stable people with COPD from three clinical sites in Spain, Italy and Germany. Over 1 year, participants will attend quarterly in-person visits to collect clinical data, while being continuously monitored using six unobtrusive smart sensing devices collecting daily metrics calculated from triaxial acceleration, angular velocity, photoplethysmogram, sound intensity, changes in latitude and longitude, ambient light intensity, biomechanical pressure and respiratory airflow parameters. Clinical outcomes are exacerbation onset through medical records; 3-month changes in HRQoL through the COPD Assessment Test and the Clinical COPD Questionnaire; 3-month changes in dyspnoea severity through the modified Medical Research Council Dyspnoea Scale; and 6-month changes in functional exercise capacity through the 6-minute walk test. We will train, internally validate and test AI-based models (Random Forests, XGBoost, multilayer perceptrons, cumulative link model and standard classification model) to predict clinical outcomes. Ethical approval was issued for all sites by the Ethical Commission (EC) of the Medical Association of Schleswig-Holstein (Bad Segeberg; vote 074/23 ff), EC of the Tuscany Region-North West Area (Pisa; vote CET10/2023) and EC of Parc de Salut Mar (Barcelona; vote 2023/11230). All participants will sign a written informed consent. NCT06172712.

Our goal was to develop a simulation platform for photon-counting CT (PCCT) imaging in mouse models of head and neck squamous cell carcinoma (HNSCC). High-resolution vasculature from an energy-integrating detector micro-CT scan of a barium-enhanced mouse was transferred to the mouse whole-body (MOBY) digital phantom using affine warps. To generate tumors with contrast agent distributions derived from real data, we trained a denoising diffusion probabilistic model (DDPM) on material-decomposed iodine- and barium-enhanced mouse tumors from a prior PCCT study. DDPM synthesized tumors were fused with the vascularized MOBY to create mouse HNSCC phantoms. We improved the accuracy of images from MATLAB PCCT simulation through an adjustment that utilizes matrix multiplication and a multi-layer perceptron (MLP) trained on matched real and simulated material phantoms. We passed MOBY HNSCC phantoms into the adjusted simulation, decomposed PCCT images into water, iodine, calcium, and barium maps, and compared these outputs to the true HNSCC phantoms using quantitative metrics from iodine- and barium-enhanced regions of the tumor. DDPM synthesized tumors had similar mean iodine and barium concentrations to real tumors. In a test set phantom, our matrix multiplication and MLP adjustment substantially reduced the root mean square error of attenuation measurements in reconstructed images from PCCT simulation. In this phantom, material decomposition of the adjusted image using a real sensitivity matrix produced similar material concentrations and cross-contamination patterns to those from real PCCT imaging. Material maps from adjusted simulations of MOBY HNSCC phantoms suggest that default PCCT settings slightly overestimated iodine content, while barium content was slightly underestimated in high barium tumors and overestimated in low barium tumors. This work established a PCCT simulation pipeline with ground truth digital mouse HNSCC phantoms, enabling evaluation of PCCT performance within a calibrated imaging configuration while minimizing radiation exposure to live mice.

Active physical human-exoskeleton interaction has been widely studied. However, the challenges of human motion intention recognition and synchronous tracking have not been well-addressed. In this article, a motion intention recognition method based on biophysical information fusion and adaptive learning was proposed to overcome the limitations of existing approaches. First, a lower-limb joint angle prediction model was developed by integrating surface electromyography (sEMG), historical joint angles and centers of gravity. The convolutional neural network, Mamba network, and multilayer perceptron network were used respectively for feature extraction, information fusion, and joint angle prediction. Second, an online adaptive method for the angle prediction model was designed based on a style transfer mapping technique to address the issue of recognition accuracy decline. In this method, the new sEMG features were mapped into the initial feature space, by which the prediction model can maintain the predictive performance during long-term implementation. Furthermore, a real-time control method for the exoskeleton synchronous tracking was given based on the predicted angles. Finally, the feasibility of the proposed methods was validated through the offline and online experiments.

Sepsis is a high-burden, highly heterogeneous clinical challenge that affects up to 30% of ICU patients. Reliable early prediction is essential for timely intervention and improved outcomes. We aimed to develop and validate a machine-learning model for predicting sepsis onset beyond the first 24 h of ICU admission. Data from septic patients were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III) database. Feature selection was performed with the Boruta algorithm. Nine algorithms-XGBoost-DART, Gaussian Naïve Bayes, LightGBM-DART, Random Forest, AdaBoost, Multi-Layer Perceptron (MLP), Support Vector Machine (SVM-RBF), k-Nearest Neighbors (KNN), and Ridge Regression-were trained and comprehensively evaluated with respect to discrimination, calibration, and clinical utility. Class imbalance was addressed using SMOTE on the training set and cost-sensitive learning for applicable algorithms. Among 1,634 ICU patients included (after excluding those meeting Sepsis-3 criteria within the first 24 h), 349 (21.4%) developed sepsis after the 24-hour observation window. AUROCs ranged from 0.794 to 0.881 across the nine models. AUROCs ranged from 0.810 to 0.895 across the nine models. XGBoost-DART achieved the highest AUROC (0.881, 95% CI: 0.854-0.908) along with the best accuracy (0.847), F1-score (0.762), and specificity (0.897). Decision-curve analysis demonstrated that XGBoost-DART delivered the greatest net benefit over the widest range of threshold probabilities, underscoring its strong clinical utility. In summary, machine-learning models provide a reliable tool for early sepsis prediction in the ICU. The XGBoost-DART model, with its outstanding performance, empowers clinicians to identify high-risk patients and initiate timely interventions to reduce mortality.

Heart failure (HF) is a heterogeneous syndrome affecting over 60 million individuals globally. Patients with hypertension are particularly susceptible to developing HF. Therefore, timely identification and predictive assessment of HF risk have significant clinical implications in this population. Thus, this study aimed to develop a new interpretable machine learning (ML) model for HF prediction. Using data from the Systolic Blood Pressure Intervention Trial (SPRINT), a random under-sampling technique was applied to address class imbalance in the target variable, achieving a 1:1 ratio between positive and negative samples. By randomly matching 162 individuals without HF events to those with events, a balanced dataset comprising 324 participants was constructed. The test set comprised 40% of the total dataset to ensure a robust evaluation of model performance. Seven ML algorithms, including support vector machine (SVM), adaptive boosting (Adaboost), naïve Bayes (NB), logistic regression (LR), gradient boosting machine (GBM), random forest (RF), and multilayer perceptron (MLP), were employed to construct the predictive models. Model performance was evaluated using the area under the curve (AUC), decision curve analysis (DCA), calibration curves, and other metrics. The SHapley Additive exPlanations (SHAP) approach was employed to rank feature significance and provide interpretability for the final model. Over a median follow-up of 3.88years, 162 patients (1.8%) developed incident HF. Among the seven ML models, GBM demonstrated the best performance. A total of 14 features were retained after the least absolute shrinkage and selection operator (LASSO) selection. The final model exhibited robust predictive capability for identifying HF risk, with an overall accuracy of 0.731, a precision of 0.770, and an AUC (95% confidence interval (CI)) of 0.763 (0.676-0.840). The GBM-based explainable prediction model demonstrated robust performance in predicting HF risk among patients with hypertension.

Deep learning frameworks have been developed for interpreting single-cell RNA sequencing (scRNA-seq) data and have demonstrated excellent performance across a range of tasks. However, existing methods remain limited in their ability to characterize heterogeneity at the individual level. To address this gap, we present scHILL, a framework that integrates a masked autoencoder (MAE) with a multilayer perceptron (MLP) to decipher phenotypic heterogeneity arises from immune cell heterogeneity among individuals under specific disease conditions. The MAE, pretrained with data augmentation, enables self-supervised feature learning without labels and effectively mitigates the challenge of limited sample size. The MLP further generates a score for each individual to quantify the functional significance of cells and genes. Across multiple datasets, scHILL outperforms existing methods in phenotype prediction and reveals individual-level immune cell heterogeneity in infectious disease, autoimmune disease, and cancer. scHILL provides a generalizable framework for interpreting individual-level scRNA-seq data, thereby facilitating the future realization of personalized medicine.

Molybdenum carbide nanoparticles (α-MoC1- x NPs) are promising catalysts that offer noble-metal-like performance at lower cost. We report a mild continuous-flow synthesis of α-MoC1- x NPs from Mo(CO)6, coupled with in-line spectroscopic monitoring and machine learning (ML)-based analysis to quantify precursor conversion and product formation in real time. A multilayer perceptron ML model was found to accurately deconvolute complex, nonlinear spectral patterns, enabling identification of a two-step reaction pathway, involving precursor conversion to an amorphous intermediate followed by intraparticle crystallization to α-MoC1- x NPs, with the first step being rate limiting. Ex situ small angle X-ray scattering (SAXS) and X-ray diffraction (XRD) validation confirm the predicted concentration profiles and crystallization behavior. This integrated approach showcases how ML can empower insights into NP nucleation and growth, paving the way for self-driving, flow-based platforms for NP synthesis.

Accurate mapping of water and vegetation is crucial for environmental monitoring, resource management, and land use planning. This study presents the application of a novel deep learning architecture, Kolmogorov-Arnold Networks (KANs), featuring learnable activation functions, for a pixel-based classification of water and vegetation using Sentinel-2 imagery. A dataset from 2023 observations, consisting of nine major global rivers-Amazon, Karun, Ganges, Mississippi, Nile, Rhine, Seine, Shatt-al-Arab, and Yangtze-was used to evaluate the performance of KANs against a baseline multi-layer perceptron (MLP) model. The results indicate that KANs achieved a general kappa coefficient of 0.9949, comparable to the MLP's 0.995, while offering a more compact architecture. The adaptive B-spline activation functions in KANs demonstrated particular effectiveness in classifying mixed and boundary pixels, areas where conventional algorithms often struggle. A sensitivity analysis further revealed KANs' robustness, achieving 99.52% accuracy with only Red and Near-Infrared bands' information, which highlights their potential for effective classification with limited spectral information. While KANs did not consistently outperform MLPs across all regions, their comparable accuracy, enhanced interpretability, and efficient training make them a promising alternative for remote sensing applications.

This study established an integrated analytical method based on near-infrared spectroscopy (NIRS) for the rapid, non-destructive, and quantitative detection of four major nutritional components in faba beans: starch, protein, moisture, and dietary fiber. By systematically comparing individual and combined spectral preprocessing strategies, optimal preprocessing combinations for each component were identified. Seven feature wavelength selection algorithms, including Competitive Adaptive Reweighted Sampling (CARS), were employed to extract key spectral variables. Predictive models were subsequently developed using four modeling approaches: Partial Least Squares (PLS), Random Forest (RF), Support Vector Machine (SVM), and Multilayer Perceptron (MLP). The results demonstrated that combined preprocessing methods significantly outperformed single techniques. The CARS algorithm exhibited the most robust performance in feature extraction, and the MLP model consistently surpassed traditional machine learning methods in predicting all components. The optimal modeling pipelines for each component were ultimately determined as follows: starch (MLP + CARS + MSC + SG + MSS, R2 = 0.92), protein (MLP + CARS + SD + SNV + MSC + MSS, R2 = 0.94), moisture (MLP + SPA + SG + SNV, R2 = 0.9973), and dietary fiber (MLP + PCA + FD + SNV, R2 = 0.9999). This study verifies the effectiveness of combining NIRS with deep learning for the simultaneous detection of multiple components in faba beans and provides a reliable methodological framework for the non-destructive quality assessment of agricultural products.

Lost circulation, which refers to the unintended loss of drilling fluid into underground formations, presents a significant challenge in drilling operations. This issue often leads to considerable non-productive time and financial losses. To effectively address this problem, it is crucial to accurately predict loss zones, volumes, and the extent of fluid invasion. This study introduces an innovative approach by integrating petrophysical well logs with drilling operational parameters and mud characteristics within a machine learning framework. Using a comprehensive dataset of 246,620 data points from 73 wells in an Iranian oil field, we developed three advanced predictive models: multi-layer perceptron (MLP), Kolmogorov-Arnold network (KAN), and a novel hybrid MLP-KAN architecture. Performance evaluations revealed that the hybrid model significantly outperformed the standalone models, achieving a determination coefficient (R2) of 0.9445 and a root mean square error of 0.0143. In contrast, the standalone MLP model achieved an R2 of 0.9054, while the KAN model reached an R2 of 0.9075. The hybrid framework effectively identified three primary mud invasion zones within the field, located at depths of 1800-2000 m, 2300-2600 m, and 2800-3000 m, accurately quantifying their average invasion volumes and radii. SHAP analysis indicated that the most significant predictive features included sonic transit time (DT), bit size, mud weight, and calcium content, aligning the model's output with established principles of drilling physics. The findings from this research provide a robust and interpretable tool for proactive management of lost circulation, enabling operators to implement zone-specific prevention strategies, optimize drilling fluid programs, and notably reduce operational risks and costs. The framework enables proactive loss prevention through early zone identification and targeted mitigation strategies, offering a scalable solution for enhancing drilling efficiency and reducing operational risks. Overall, this work bridges the gap between data-driven analytics and practical field applications, offering a scalable solution for enhancing drilling efficiency.

In this study, an enhanced Active Disturbance Rejection Control (ADRC) strategy is developed for gas turbine systems to achieve superior dynamic performance and robustness. The proposed scheme employs a linear ADRC for fuel regulation and a novel nonlinear ADRC for rotor speed control. Specifically, a multilayer perceptron neural network is integrated with an adaptive term into the extended state observer architecture, effectively handling unmodeled dynamics and external disturbances. To ensure optimal control performance, a fractional-order fuzzy particle swarm optimization algorithm is introduced as a high-dimensional tuning framework. By dynamically adjusting learning factors through fuzzy logic and utilizing fractional-order calculus, this framework overcomes the convergence limitations of standard optimization techniques when tuning multiple interdependent parameters. Simulation results demonstrate that the proposed method yields faster transient responses and significantly higher robustness against disturbances and uncertainties compared to conventional approaches.

Chronic Kidney Disease (CKD) is associated with high 30-day hospital readmission rates due to progressive renal dysfunction, multiple comorbidities, and complications related to dialysis and catheter use. Artificial Intelligence (AI) and Machine Learning (ML) offer promising tools for early identification of high-risk patients. To develop and evaluate ML models for predicting 30-day hospital readmission among CKD patients and identify key clinical and laboratory predictors related to readmission risk. This retrospective study analyzed 277 hospitalized patients with CKD at Hasheminejad Kidney Center (2019-2022). Forty-four demographic, clinical, and laboratory features were included. Preprocessing included handling missing data, normalization, outlier removal, categorical encoding, and oversampling. Six ML models, including eXtreme Gradient Boosting (XGBoost), Random Forest, Decision Tree, AdaBoost, Multilayer Perceptron (MLP), and Logistic Regression, were trained using a 70/30 train-test split with cross-validation. Feature selection employed SHAP values, mutual information, F-values, SVM, and chi-squared tests. XGBoost outperformed other models (accuracy > 90%). The strongest predictors were estimated Glomerular Filtration Rate (eGFR), Blood Urea Nitrogen (BUN) and creatinine levels, age, presence of diabetes mellitus and hypertension, catheter-related infection, and triglycerides, intact Parathyroid hormone (iPTH), and albumin levels. Catheter infection emerged as a modifiable, high-impact predictor. The SHAP values analysis confirmed strong contributions of kidney function markers, inflammatory indicators, and metabolic variables to re-admission risk. ML-based prediction models, particularly XGBoost, demonstrated high accuracy in identifying CKD patients at risk of 30-day readmission. Integration of these models into clinical workflows may improve early intervention, reduce hospital readmissions, and support evidence-based nephrology care.

Heating systems that combine air-source heat pumps with phase-change energy storage tanks can effectively utilize off-peak electricity and enhance energy storage efficiency. However, in actual industrial building heating operations, the system's thermal characteristics are influenced by multiple factors, making it challenging for traditional single-factor prediction models to accurately capture their dynamic behavior. To address this issue, this paper develops a novel prediction model called XMS (XGBoost, MLP, and Stacking model). First, heating data from an operational air-source heat pump system coupled with a phase-change energy storage tank are collected. Second, the XMS model is proposed, based on a stacking ensemble strategy. It integrates XGBoost and a multi-layer perceptron (MLP) as base learners and employs a meta-learner to perform secondary modeling of their outputs. Finally, the XMS model is compared with a traditional MLP model. The results indicate that the XMS model demonstrates significantly superior predictive performance compared to the MLP model, achieving a 22.5% reduction in root mean square error (RMSE) and a 10.1% increase in the coefficient of determination (R²). The XMS model better captures the nonlinear and multivariate coupling characteristics of the heating system. This study provides an efficient and reliable modeling method for load forecasting and control optimization in air-source heat pump phase-change energy storage heating systems, offering valuable guidance for intelligent heating control technology.

Large language models (LLMs) are increasingly investigated for their potential role in guideline-based clinical information support. However, their consistency with subspecialty guidelines, particularly in urolithiasis, remains underexplored. This study aimed to evaluate the performance of four large language models (LLMs); GPT-4, GPT-4-turbo, Claude, and Gemini in generating guideline-concordant responses to clinical questions related to urolithiasis. A total of 105 clinical questions were independently developed by the authors based on urolithiasis management principles. Each LLM generated responses in two separate sessions. Two experienced urologists evaluated the outputs for accuracy and concordance with guideline recommendations. Inter-rater agreement analysis demonstrated fair agreement between evaluators. Differences across models and guideline categories were assessed using appropriate statistical tests. All four LLMs demonstrated high guideline adherence, with mean total scores ranging from 86.5&#x2009;&#xb1;&#x2009;5.2 (Gemini) to 92.8&#x2009;&#xb1;&#x2009;3.1 (Claude). Claude achieved the highest correlation with expert ratings (r&#x2009;=&#x2009;0.94, p&#x2009;<&#x2009;0.01). There were no statistically significant differences across models or among the nine clinical categories (p&#x2009;>&#x2009;0.05). Session-to-session repeatability was also high for all models, with intra-model correlation coefficients exceeding 0.90. LLMs, particularly Claude, can provide reliable, guideline-consistent answers to urolithiasis-related clinical queries. Their consistent performance across themes suggests utility as adjunctive informational tools for guideline-based urological education and support, although further validation in real-world clinical settings remains necessary.

The adoption and acceptance of parental control apps (PCAs) are threatened by many factors, even though mobile applications are at the forefront of mobile computing technologies. Existing studies indicate that PCA adoption can be improved by understanding users' behavioral intention and mindsets. Several adoption studies show that task features are among the most influential factors influencing users' perceptions of mobile applications. The role of PCA features, such as digital etiquette, cyberbullying, child tracking, and family values, remains largely unexamined in current research. Thus, by using task-technology fit (TTF) theory, this study examines how task-technology features and characteristics affect the behavioral intention of parents toward PCA adoption within the context of Saudi Arabia. To empirically test the proposed theoretical model, data were collected from 388 parents in Saudi Arabia. A multistage analysis, which consists of partial least squares structural equation modeling (PLS-SEM), partial least squares prediction algorithms (PLS-predict), and artificial neural networks (ANN), was employed to examine the outcome of PCA behavioral adoption. The results demonstrate that digital etiquette, cyberbullying, family values, and parental mediation significantly and positively influence TTF, whereas mobility, child tracking, and inappropriate online content do not have a significant impact. Furthermore, TTF was found to be a significant predictor of parents' behavioral intention toward PCA adoption. These findings can be utilized to enhance the design of PCAs and thus the user experience for both parents and children. Moreover, this study extends and contributes to the understanding of task features in the context of PCAs through the TTF model.

Spiking neural networks (SNNs) are hybrid dynamical systems that operate on spatiotemporal data, yet their learnable parameters are often limited to synaptic weights, contributing little to temporal pattern recognition. Learnable parameters that delay spike times can improve classification performance in temporal tasks, but existing methods rely on large networks and offline learning, making them unsuitable for real-time operation in resource-constrained environments. In this paper, we introduce synaptic and axonal delays to leaky integrate and fire (LIF)-based feedforward and recurrent SNNs, and propose three-factor learning rules to simultaneously learn weights and delays online. We employ a smooth Gaussian surrogate to approximate spike derivatives exclusively for the eligibility trace calculation, and together with a top-down error signal determine parameter updates. Our experiments show that incorporating delays improves accuracy by up to 18% over a weights-only baseline, and for networks with similar parameter counts, jointly learning weights and delays yields up to 14% higher accuracy. On the SHD speech recognition dataset, our method achieves similar accuracy to offline backpropagation-based approaches. Compared to state-of-the-art methods, it reduces model size by 6.6&#xd7; and inference latency by 50%, with only a 2.5% drop in classification accuracy. Our findings would be beneficial for the design of power and area-constrained neuromorphic processors by enabling on-device learning and lowering memory requirements.

The diagnosis of Alzheimer's disease (AD) has progressively depended on sophisticated neuroimaging methods alongside cognitive assessments. This study combines volumetric feature analysis with computational modeling techniques, focusing on spatial and temporal analysis, to categorize individuals as cognitively normal (CN), mild cognitive impairment (MCI), or AD using magnetic resonance imaging (MRI) data. In the initial phase, volumetric changes, comprising cortical thickness, white matter, grey matter, cerebrospinal fluid, and total intracranial volume, were derived from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset utilizing the CAT12 toolbox in statistical parametric mapping (SPM). Linear regression was utilized on these variables over time to create slopes that reflect volumetric change rates, which then served as inputs for machine learning classifiers. The slopes of cortical thickness exhibited the greatest classification accuracy, reaching 82.5% with a random forest model for differentiating AD from CN individuals. During the second phase, a deep learning methodology was utilized, relying solely on the MRI scans and excluding the outcomes from the first phase. A pre-trained 3D ResNet-101 convolutional neural network (CNN) model extracted spatial characteristics from MRI volumes, whereas long short-term memory (LSTM) networks recorded temporal dynamics across subsequent annual scans. This hybrid CNN-LSTM design markedly improved classification performance, attaining 96.7% accuracy for AD against CN and enhancing the distinction of MCI cases. Nonetheless, discrepancies in MCI categorization were chiefly ascribed to the restricted access to annual MRI data and the model's pre-training on CN and AD cohorts. These findings highlight the potential of integrating volumetric statistical analysis with deep learning for automated AD categorization. This work enhances neuroimaging diagnostic methods by utilizing both spatial and temporal MRI data, enabling early diagnosis and better evaluation of disease development.

Foreign object detection (FOD) in autonomous driving environments poses a significant challenge due to the dual nature of anomalous objects: known objects appearing in inappropriate contexts or truly novel objects unseen during training. Existing methods typically address either closed-set semantic reasoning or open-set uncertainty estimation, limiting their ability to handle both types of anomalies effectively. This paper introduces HSAOSFOD (Hybrid Scene-Aware Open-set Foreign Object Detection), a unified lightweight framework that integrates closed-set and open-set paradigms through explicit modeling of a scene-object compatibility matrix and multi-signal open-set detection modules. The key contributions include: (1) a scene-object compatibility module that leverages domain priors to detect contextual mismatches of known objects, (2) a multi-signal fusion module that combines prototype-based novelty detection and uncertainty estimation, and (3) an efficient architectural design utilizing separable self-attention and depth wise convolutions, achieving a model size of only 4.33 million parameters. Extensive experiments on the Cityscapes and RailSem19 datasets for training, and Road Anomaly and Lost and Found datasets for evaluation, demonstrate that HSAOSFOD attains competitive performance with AUROC scores of 0.9506 on Road Anomaly and 0.6158 on Lost and Found, while preserving computational efficiency. Ablation studies confirm that the compatibility module (closed-set) contributes approximately 1.1% and the novelty detection head (open-set) contributes approximately 0.4% to average AUROC, together describing for a combined hybrid contribution of 1.5% over the base decoder alone. HSAOSFOD illustrates the potential of combining explicit domain knowledge with data-driven learning to produce efficient and interpretable hybrid models, delivering particularly strong results on context-sensitive anomalies.

NEURON has been widely used as an empirically-based simulation tool, especially for multi-compartment conductance-based neuronal modeling. The network mediating feeding in Aplysia californica has been extensively studied as a model central pattern generator. Understanding the relationship between network parameter values and their effect on animal behavior is of key importance in systems such as the Aplysia feeding apparatus, where detailed biophysical models can be constructed. This study aims to develop a new Python tool called NEURONpyxl that reads parameters from a spreadsheet to construct full neural networks to make it easier to create complex models in the NEURON simulation environment, incorporating short-term forms of plasticity such as depression or facilitation. Test simulations from well-understood networks were created in NEURONpyxl, and compared to simulation results of the same network in another neural simulator, the Simulator for Neural Networks and Action Potentials (SNNAP), which has previously been used to model conductance-based networks that include complex synaptic connections and multiple forms of synaptic plasticity. NEURONpyxl was then used to conduct a parameter grid search to optimize conductances in a previously developed network model of Aplysia feeding behavior. Simulations of the test networks in NEURONpyxl and SNNAP produced numerically equivalent results, with differences remaining within the expected margin of error arising from numerical integration and implementation details. We then located parameter values that generated simulated motor patterns with durations of protraction and retraction that matched biological feeding behavior under different mechanical loads. NEURONpyxl simplifies building and simulating complex neural networks with different forms of synaptic plasticity, and locating physiologically relevant parameter values. With NEURONpyxl, future work may include the creation of ensembles of network models and the integration of biomechanics with complex conductance-based networks.