Network Prediction Model Research Articles

Using a Neural Network Architecture for the Prediction of Neurologic Outcome for Out-of-Hospital Cardiac Arrests Using Hospital Level Variables and Novel Physiologic Markers

Out-of-hospital cardiac arrest (OHCA) is a major public health burden due to its high mortality rate, sudden nature, and long-term impact on survivors. Consequently, there is a crucial need to create prediction models to better understand patient trajectories and assist clinicians and families in making informed decisions. We studied 107 adult OHCA patients admitted at an academic Emergency Department (ED) from 2018–2023. Blood samples and ocular ultrasounds were acquired at 1, 6, and 24 h after return of spontaneous circulation (ROSC). Six classes of clinical and novel variables were used: (1) Vital signs after ROSC, (2) pre-hospital and ED data, (3) hospital admission data, (4) ocular ultrasound parameters, (5) plasma protein biomarkers and (6) sex steroid hormones. A base model was built using 1 h variables in classes 1–3, reasoning these are available in most EDs. Extending from the base model, we evaluated 26 distinct neural network models for prediction of neurological outcome by the cerebral performance category (CPC) score. The top-performing model consisted of all variables at 1 h resulting in an AUROC score of 0.946. We determined a parsimonious set of variables that optimally predicts CPC score. Our research emphasizes the added value of incorporating ocular ultrasound, plasma biomarkers, sex hormones in the development of more robust predictive models for neurological outcome after OHCA.

Assessment of Deep Neural Network Models for Direct and Recursive Multi-Step Prediction of PM10 in Southern Spain

Western Europe has been strongly affected in the last decades by Saharan dust incursions, causing a high PM10 concentration and red rain. In this study, dust events and the performance of seven neural network prediction models, including convolutional neural networks (CNN) and recurrent neural networks (RNN), have been analyzed in a PM10 concentration series from a monitoring station in Córdoba, southern Spain. The models were also assessed here for recursive multi-step prediction over different forecast periods in three different situations: background concentration, a strong dust event, and an extreme dust event. A very important increase in the number of dust events has been identified in the last few years. Results show that CNN models outperform the other models in terms of accuracy for direct 24 h prediction (RMSE values between 10.00 and 10.20 μg/m3), whereas the recursive prediction is only suitable for background concentration in the short term (for 2–5-day forecasts). The assessment and improvement of prediction models might help the development of early-warning systems for these events. From the authors’ perspective, the evaluation of trained models beyond the direct multi-step predictions allowed to fill a gap in this research field, which few articles have explored in depth.

Green Synthesis of nZVI-Modified Sludge Biochar for Cr(VI) Removal in Water: Fixed-Bed Experiments and Artificial Neural Network Model Prediction

The contamination of aquatic environments with hexavalent chromium (Cr(VI)) poses significant environmental and public health risks, necessitating the development of high-performance adsorbents for its efficient removal. This study evaluates the potential of green-synthesized nanoscale zero-valent iron-modified sludge biochar (TP-nZVI/BC) as an effective adsorbent for Cr(VI) removal through isothermal adsorption experiments, fixed-bed column studies, and artificial neural network (ANN) modeling. Fixed-bed experiments demonstrated that breakthrough time, exhaustion time, and unit adsorption capacity increased with bed height. Conversely, these parameters decreased with higher influent concentrations and flow rates. Breakthrough curve analysis revealed that the Thomas model provided the best fit for the experimental data (R2 = 0.992–0.998). An ANN model, developed using the Levenberg–Marquardt algorithm, employed a single hidden layer with six neurons and exhibited excellent predictive performance (R2 = 0.996, MSE = 0.520). The ANN model was validated for its ability to predict adsorption behavior under untested conditions, demonstrating its applicability for process optimization. This study highlights the superior performance of TP-nZVI/BC as an adsorbent for Cr(VI) and establishes a theoretical basis for optimizing and scaling up fixed-bed adsorption systems using ANN modeling. The findings provide valuable insights into the practical application of sustainable materials in environmental remediation.

Prediction Accuracy of Stackelberg Game Model of Electricity Price in Smart Grid Power Market Environment

With the deepening of power market reform and the increasingly fierce competition in the power market, the accurate prediction of electricity price has become an important demand for power market participants to make scientific decisions, optimize resource allocation, and reduce risks. Electricity price forecast can provide a key reference for the power market, help market participants make wise decisions, promote competition and efficient operation and cope with complex market fluctuations, provide a scientific basis for various entities to optimize resource allocation, reduce risks and improve benefits, and promote the sustainable development of the power industry. This study presents a dynamic retail price prediction method for smart grid based on the Stackelberg game model. Firstly, the correlation test is used to verify the strong correlation between electric load and electricity price. Secondly, the parameters of the Stackelberg model are determined, and the load and electricity price are tested using the white noise test. Finally, by comparing the BP neural network model and quantifying the model parameters, the superiority of the model is verified. The results show that the Stackelberg game model has higher prediction accuracy than the BP neural network model in electricity price prediction.

A Bayesian regularization back propagation (BRBP) neural network model for prediction of the effect of using Al2O3–Fe2O3 hybrid nano fuels on the performance and emissions of diesel engines

A Bayesian regularization back propagation (BRBP) neural network model for prediction of the effect of using Al2O3–Fe2O3 hybrid nano fuels on the performance and emissions of diesel engines

An oral microbiota-based deep neural network model for risk stratification and prognosis prediction in gastric cancer

ABSTRACT Background This study aims to develop an oral microbiota-based model for gastric cancer (GC) risk stratification and prognosis prediction. Methods Oral microbial markers for GC prognosis and risk stratification were identified from 99 GC patients, and their predictive potential was validated on an external dataset of 111 GC patients. The identified bacterial markers were used to construct a Deep Neural Network (DNN) model, a Random Forest (RF) model, and a Support Vector Machine (SVM) model for predicting GC prognosis. Results GC patients with <3 years of survival showed a higher abundance of Aggregatibacter and diminished abundances of Filifactor and Moryella than those who survived ≥3 years. The Boruta algorithm unearthed Leptotrichia as another significant marker for GC prognosis. Consequently, a DNN model was constructed based on the relative abundances of these bacteria, predicting 3-year and 5-year survival in GC patients with Area Under Curve of 0.814 and 0.912, respectively. Notably, the DNN model outperformed the TNM staging system, SVM and RF models. The prognostic value of these bacterial markers was further reinforced by external validation. Conclusion The oral microbiota-based DNN model may advance GC prognosis. The biological functions of these oral bacterial markers warrant further investigation from the perspective of GC progression.

What is the best brain state to predict autistic traits?

Autism is a heterogeneous condition, and functional magnetic resonance imaging-based studies have advanced understanding of neurobiological correlates of autistic features. Nevertheless, little work has focused on the optimal brain states to reveal brain-phenotype relationships. In addition, there is a need to better understand the relevance of attentional abilities in mediating autistic features. Using connectome-based predictive modelling, we interrogate three datasets to determine scanning conditions that can boost prediction of clinically relevant phenotypes and assess generalizability. In dataset one, a sample of youth with autism and neurotypical participants, we find that a sustained attention task (the gradual onset continuous performance task) results in high prediction performance of autistic traits compared to a free-viewing social attention task and a resting-state condition. In dataset two, we observe the predictive network model of autistic traits generated from the sustained attention task generalizes to predict measures of attention in neurotypical adults. In dataset three, we show the same predictive network model of autistic traits from dataset one further generalizes to predict measures of social responsiveness in data from the Autism Brain Imaging Data Exchange. In sum, our data suggest that an in-scanner sustained attention challenge can help delineate robust markers of autistic traits and support the continued investigation of the optimal brain states under which to predict phenotypes in psychiatric conditions.

Robust estimation of skin physiological parameters from hyperspectral images using Bayesian neural networks.

Machine learning models for the direct extraction of tissue parameters from hyperspectral images have been extensively researched recently, as they represent a faster alternative to the well-known iterative methods such as inverse Monte Carlo and inverse adding-doubling (IAD). We aim to develop a Bayesian neural network model for robust prediction of physiological parameters from hyperspectral images. We propose a two-component system for extracting physiological parameters from hyperspectral images. First, our system models the relationship between the measured spectra and the tissue parameters as a distribution rather than a point estimate and is thus able to generate multiple possible solutions. Second, the proposed tissue parameters are then refined using the neural network that approximates the biological tissue model. The proposed model was tested on simulated and in vivo data. It outperformed current models with an overall mean absolute error of 0.0141 and can be used as a faster alternative to the IAD algorithm. Results suggest that Bayesian neural networks coupled with the approximation of a biological tissue model can be used to reliably and accurately extract tissue properties from hyperspectral images on the fly.

Predictive value of a constructed artificial neural network model for microvascular invasion in hepatocellular carcinoma: A retrospective study.

Microvascular invasion (MVI) is a significant risk factor for recurrence and metastasis following hepatocellular carcinoma (HCC) surgery. Currently, there is a paucity of preoperative evaluation approaches for MVI. To investigate the predictive value of texture features and radiological signs based on multiparametric magnetic resonance imaging in the non-invasive preoperative prediction of MVI in HCC. Clinical data from 97 HCC patients were retrospectively collected from January 2019 to July 2022 at our hospital. Patients were classified into two groups: MVI-positive (n = 57) and MVI-negative (n = 40), based on postoperative pathological results. The correlation between relevant radiological signs and MVI status was analyzed. MaZda4.6 software and the mutual information method were employed to identify the top 10 dominant texture features, which were combined with radiological signs to construct artificial neural network (ANN) models for MVI prediction. The predictive performance of the ANN models was evaluated using area under the curve, sensitivity, and specificity. ANN models with relatively high predictive performance were screened using the DeLong test, and the regression model of multilayer feedforward ANN with backpropagation and error backpropagation learning method was used to evaluate the models' stability. The absence of a pseudocapsule, an incomplete pseudocapsule, and the presence of tumor blood vessels were identified as independent predictors of HCC MVI. The ANN model constructed using the dominant features of the combined group (pseudocapsule status + tumor blood vessels + arterial phase + venous phase) demonstrated the best predictive performance for MVI status and was found to be automated, highly operable, and very stable. The ANN model constructed using the dominant features of the combined group can be recommended as a non-invasive method for preoperative prediction of HCC MVI status.

Transfer learning-based deep neural network model for performance prediction of hydrogen-fueled solid oxide fuel cells

Transfer learning-based deep neural network model for performance prediction of hydrogen-fueled solid oxide fuel cells

Neural network quantification for solar radiation prediction: An approach for low power devices

Accurate solar radiation prediction leverages various machine learning techniques, with artificial neural networks (ANN) being the most common and precise due to their ability to detect and learn relationships between meteorological variables and solar radiation. Traditionally, training and deploying these models require high-capacity computers. However, the proliferation of low-power smart devices, such as embedded systems and mobile devices, necessitates exploring methodologies for implementing ANN on systems with limited computational resources. This paper proposes a quantized neural network model for solar radiation prediction, considering the hardware limitations of low-power devices like the Raspberry Pi RP2040 microcontroller. The methodology involves five stages: hardware and software selection, neural network development and quantization, microcontroller implementation, model validation, and result analysis. Experimental design allows detailed performance evaluation of quantized neural networks, demonstrating that the TensorFlow Lite Quantized Aware model is suitable for solar radiation prediction. Metrics such as root mean square error (RMSE) of 44.24 and R² of 0.96 indicate that the selected quantized model differs from the original non-quantized model by less than 0.5% in RMSE and 0.04% in R². The study concludes that implementing quantized ANN models on microcontrollers is a technically and economically viable solution for solar radiation prediction. Quantization enables complex predictive models to run on low-cost, energy-efficient devices, thereby democratizing advanced prediction technologies for critical applications like solar energy generation.

ZeRPI: A Graph Neural Network Model for Zero-Shot Prediction of RNA-Protein Interactions.

RNA-protein interactions are crucial for biological functions across multiple levels. RNA binding proteins (RBPs) intricately engage in diverse biological processes through specific RNA molecule interactions. Previous studies have revealed the indispensable role of RBPs in both health and disease development. With the increase of experimental data, machine-learning methods have been widely used to predict RNA-protein interactions. However, most current methods either train models for individual RBPs or develop multi-task models for a fixed set of multiple RBPs. These approaches are incapable of predicting interactions with previously unseen RBPs. In this study, we present ZeRPI, a zero-shot method for predicting RNA-protein interactions. Based on a graph neural network model, ZeRPI integrates RNA and protein information to generate detailed representations, using a novel loss function based on contrastive learning principles to augment the alignment between interacting pairs in feature space. ZeRPI demonstrates competitive performance in predicting RNA-protein interactions across a wide array of RBPs. Notably, our model exhibits remarkable versatility in accurately predicting interactions for unseen RBPs, demonstrating its capacity to transfer knowledge learned from known RBPs.

An artificial neural network and Levenberg-Marquardt training algorithm-based mathematical model for performance prediction

This research seeks to propose an innovative mathematical approach for measuring students’ performance in engineering education. The numerical solutions to this mathematical model and a thorough analysis are included in this study. Four categories – average candidates, poor candidates, below average candidates, and good candidates – are used to build the mathematical model that was built. To solve the differential system based on the migration rate and average student rate moving to weak and above average, the Adams numerical scheme is applied to the numerical results of the designed nonlinear mathematical model. Moreover, an artificial neural network is also applied to get the stochastic results of ANNs-LMB, also known as the Levenberg-Marquardt training algorithm. The ANNs-LMB procedures have been implemented with three samples of data scales using the authentication, testing and training, which are chosen as 75%, 15% and 10%, respectively. According to the findings, when the rate of students leaving engineering studies increased, good students performed better, and when the rate of students below average moved, it was due to an increase in the rate of migration above average, the performance of the good students was only impacted in this way. This research material can be used in different designs and models to improve the students’ performance.

Research on Utility Analysis and Risk Prediction of Economic Management of Construction Enterprises in Digital Economy

This paper determines the evaluation index system of economic management utility and prediction of construction enterprises based on the theory of sustainable development of the construction industry, the theory of economics, and the principle of construction of evaluation index system. Information entropy and fuzzy evaluation are used to measure the economic management utility of construction enterprises in the digital economy. And the economic management risk aspect is analyzed by BP neural network model for prediction. After analyzing, the comprehensive evaluation results of the economic management utility of the construction enterprise [3.9848, 3.2449, 1.2547, 0.5276, 0.9895] indicate that the economic management utility of the construction enterprise is in the excellent. Based on the results of risk prediction of economic management of the construction enterprise ( R 2 = 0.9842), it was confirmed that the model has a good ability to predict the risk of economic management. The results of the study make the economic management of construction enterprises better guaranteed and stabilize the development of the regional basic economy to a certain extent.

Energy efficiency optimization analysis of a ground source heat pump system based on neural networks and genetic algorithms

This paper reports on the performance of a ground source heat pump (GSHP) system located in Shandong Province, China. The system operation data were monitored and collected by a data collection system. According to the analysis of the accumulated operational data, it was found that the GSHP system showed a relative higher COP in cooling season of 2023 than that of 2022 due to the change of supplying water temperature at ground-source side. Based on the analyzed data, a BP neural network model for energy consumption prediction was established. Furthermore, genetic algorithm (GA) was used to optimize the control strategy on the basis of the energy consumption prediction model. Comparison between the artificial experience control strategy and the one optimized by the genetic algorithm was conducted. The results show that the optimization strategy of the genetic algorithm is superior in terms of energy saving, particularly in the load rate higher than 50%, in which, the average energy-saving rate reaches 39.66%. Within the load rate range of 30–50%, the energy-saving rate could also reach 7.84%.

Artificial Neural Networks Model for Photosynthetic Rate Prediction of Leaf Vegetable Crops under Normal and Nutrient-Stressed in Greenhouse

Photosynthesis is one of the essential processes in plant physiology that produces glucose and oxygen to support plant growth. Nutrient stress conditions will affect the photosynthetic rate in plants. The model predicting photosynthetic rates based on environmental conditions, nutrients, and plant types will be highly beneficial for farmers in tweaking these variables to maximize plant photosynthesis. This research focused on assessing the impact of nutrient stress on the photosynthetic rate in leaf vegetable crops and aimed to create a model using artificial neural networks (ANN) to predict photosynthetic rates under nutrient-stress conditions. Leaf vegetable crops were cultivated in a greenhouse using the NFT hydroponic system with eight nutrient conditions. This paper introduces an ANN model featuring nine input variables, ten hidden layers, and a single output. This model aims to elucidate the relationship between these inputs and the output parameter. The statistical analysis revealed a notable disparity in the CO2 assimilation rate among leaf vegetable crops subjected to nutrient stress treatment. The constructed ANN model demonstrated strong performance, achieving an R2 value of 0.9416, an RMSE of 1.5898 during training, and an R2 value of 0.9271 with an RMSE of 1.9649 in validation. A combination of statistical analysis and ANN modeling accurately explained the relationship and influence of input parameters, especially nutrient stress conditions, on the photosynthetic rate of leaf vegetable plants cultivated hydroponically in a greenhouse.

Graph Fuzzy Attention Network Model for Metastasis Prediction of Prostate Cancer Based on mRNA Expression Data

Graph Fuzzy Attention Network Model for Metastasis Prediction of Prostate Cancer Based on mRNA Expression Data

A Multiple Controlled Toffoli Driven Adaptive Quantum Neural Network Model for Dynamic Workload Prediction in Cloud Environments.

The key challenges in cloud computing encompass dynamic resource scaling, load balancing, and power consumption. Accurate workload prediction is identified as a crucial strategy to address these challenges. Despite numerous methods proposed to tackle this issue, existing approaches fall short of capturing the high-variance nature of volatile and dynamic cloud workloads. Consequently, this paper introduces a novel model aimed at addressing this limitation. This paper presents a novel Multiple Controlled Toffoli-driven Adaptive Quantum Neural Network (MCT-AQNN) model to establish an empirical solution to complex, elastic as well as challenging workload prediction problems by optimizing the exploration, adaption, and exploitation proficiencies through quantum learning. The computational adaptability of quantum computing is ingrained with machine learning algorithms to derive more precise correlations from dynamic and complex workloads. The furnished input data point and hatched neural weights are refitted in the form of qubits while the controlling effects of Multiple Controlled Toffoli (MCT) gates are operated at the hidden and output layers of Quantum Neural Network (QNN) for enhancing learning capabilities. Complimentarily, a Uniformly Adaptive Quantum Machine Learning (UAQL) algorithm has evolved to functionally and effectually train the QNN. The extensive experiments are conducted and the comparisons are performed with state-of-the-art methods using four real-world benchmark datasets. Experimental results evince that MCT-AQNN has up to 32%-96% higher accuracy than the existing approaches.

Soot temperature and volume fraction field predictions via line-of-sight soot integral radiation equation informed neural networks in laminar sooting flames

This paper originally proposes a physics informed neural networks (PINNs) model for the simultaneous prediction of soot temperature and volume fraction fields in laminar flames from experimental soot integral radiation. Contrasted with the previous data-driven models, the PINNs model incorporates the line-of-sight soot radiation integral equation into the model architecture. Doing so, the superiority of the physics informed neural networks model is displayed in terms of prediction accuracy under limited training data size and training efficiency. Due to the significant reduction of training experimental data dependence, such gray-box physics informed methodology sheds light on practical combustion devices combustion monitoring, i.e., limited optical window endoscope engines.

A Bayesian Network Approach to Lung Cancer Screening: Assessing the Impact of Data Quantity, Quality, and the Combination of Data from Danish Electronic Health Records.

Background/Objectives: Lung cancer (LC) is the leading cause of cancer mortality, making early diagnosis essential. While LC screening trials are underway globally, optimal prediction models and inclusion criteria are still lacking. This study aimed to develop and evaluate Bayesian Network (BN) models for LC risk prediction using a decade of data from Denmark. The primary goal was to assess BN performance on datasets varying in size and completeness, simulate real-world screening scenarios, and identify the most valuable data sources for LC screening. Methods: The study included 38,944 patients evaluated for LC, with 11,284 (29%) diagnosed. Data on comorbidities, medications, and general practice were available for the entire cohort, while laboratory results, smoking habits, and other variables were only available for subsets. The cohort was divided into four subsets based on data availability, and BNs were trained and validated across these subsets using cross-validation and external validation. To determine the optimal combination of variables, all possible data combinations were evaluated on the samples that contained all the variables (n = 5587). Results: A model trained on the small, complete dataset (AUC 0.78) performed similarly on a larger dataset with 21% missing data (AUC 0.78). Performance dropped when 39% of data were missing (AUC 0.67), resulting in informative variables missing completely in the dataset. Laboratory results and smoking data were the most informative, significantly outperforming models based only on age and smoking status (AUC 0.70). Conclusions: BN models demonstrated moderate to strong predictive performance, even with incomplete data, highlighting the potential value of incorporating laboratory results in LC screening programs.