High Prediction Research Articles

Is predictability of the conditioning stimulus (CS) a critical factor in conditioned pain modulation (CPM)?

Introduction Conditioned pain modulation (CPM) allows to investigate endogenous pain modulation and its clinical outcomes. Although co-activation of emotions has been shown to affect CPM, the impact of ‘threat,’ which may accompany CPM stimulation itself, has been mostly neglected. A critical factor for the threat level of the conditioning stimulus (CS) may be its predictability. Methods 38 healthy participants (18 female) took part in a CPM study with pressure stimulation on the leg (blood-pressure cuff) serving as CS and heat stimulation on the forearm (contact thermode; CHEPS) serving as test stimulus (TS). While CS varied in intensity and –as operationalisation of threat– in temporary predictability, TS was kept constant. CPM effects were studied by EEG parameters (N2P2) and pain ratings. Results We found a significant CPM effect when considering N2P2, with low CS predictability augmenting CPM inhibition; in contrast, a surprisingly facilitatory CPM effect occurred in pain ratings (in the high CS predictability condition). The threat manipulation was only partially successful because CS intensity increased the threat ratings but not -as intended- CS predictability. Correlations between subjective and psychophysiological CPM responses were low. Discussion The differing CPM effects in subjective and psychophysiological responses, with both inhibitory and facilitatory effects, is puzzling but has already been observed earlier. The consideration of the CPM stimulation as major threat that is emotionally active is theoretically clearly justifiable but the operationalisation by means of different levels of CS predictability as in the present study might not have been ideal. Thus, further attempts of experimental verification are warranted.

An Empirical Study of Data Mining Technology in English Learning Outcome Prediction

This study employs data mining to construct a predictive model for English learning outcomes, aiming to identify crucial factors affecting student performance and inform teaching enhancements. Through extensive data collection and meticulous preprocessing, a robust predictive model is established. Detailing the theoretical framework and methodologies such as machine learning, data preprocessing, feature selection, and model assessment, the study ensures model accuracy and reliability. Data sourcing and processing steps transform raw data into a model-ready feature set. Model validation reveals high prediction accuracy and generalizability, with key features significantly impacting achievement predictions, deepening insight into learning determinants and guiding targeted teaching strategies. The research concludes with a summary of findings, acknowledging limitations, and suggesting future avenues. This data-driven English learning achievement prediction model offers promising educational applications, enhancing decision-making and personalized learning.

Appraising machine learning algorithms in predicting noise level and emissions from gasoline-powered household backup generators

AbstractMachine learning is presently receiving great attention. However, machine learning applications to gasoline engine research are limited. This paper investigated the implementation of various machine learning models in predicting the emissions (CO2, CO, and PM2.5) and noise levels of gasoline-powered household generators for the first time. Data of operating and installed capacity, efficiency (input) and emissions, and noise level (output) obtained from 166 generators were used in extreme gradient boosting, artificial neural network (ANN), decision tree (DT), random forest (RF), and polynomial regression (PNR) algorithms to develop predictive models. Results revealed high prediction performance (R2 = 0.9377–1.0000) of these algorithms marked with very low errors. The implementation of PNR followed by the RF exhibited the best models for predicting CO2, CO, PM2.5, and the noise level of generators. R2 of 1.000 and 0.9979–0.9994, mean squared error of < 10−6 and 2 × 10−5–8.6 × 10−5, mean absolute percentage error of 9.15 × 10−16–1.3 × 10−15 and 7.1 × 10−3–8.1 × 10−2, and root mean squared error of 3.3 × 10−16–5.4 × 10−16 and 4.4 × 10−3–9.3 × 10−2 were recorded for all the output parameters using PNR and RF respectively. DT models had the least prediction capacity for CO, CO2, and noise levels (R2 = 0.9493–0.9592) while ANN produced the least performance for PM2.5 (R2 = 0.9377). This study further strengthens machine learning applications in engine research for the prediction of various output parameters.

A scoring model for the expression of genes related to programmed cell death predicts immunotherapy response and prognosis in lung adenocarcinoma

BackgroundLung adenocarcinoma (LUAD) continues to be the leading cause of cancer death worldwide, driven by environmental factors like smoking and genetic predispositions. LUAD has a high mortality rate, and new biomarkers are urgently needed to improve treatment strategies and patient management. Programmed cell death (PCD) is involved in tumor progression and response to treatment. Therefore, there is a need for an extensive study of the role and functions of PCD-related genes (PCDRGs) in lung adenocarcinoma so as to understand the pathophysiologic features of lung adenocarcinoma.MethodsBased on TCGA and GEO databases, this research is aimed at screening differentially expressed PCD-related genes in lung adenocarcinoma. We conducted GO, and KEGG analysis to establish the link between these genes and biological processes. By applying various machine learning algorithms such as CoxBoost analysis, we developed PCD-related indices (PCDI) that were used to verify their ability to predict prognosis with the use of other datasets. This was done in addition to exploring the biological functions of PCD genes associated with lung adenocarcinoma by assessing the relationship between immune cell components of tumor microenvironment and PCD genes together with examining how they affect drug sensitivity.ResultsThe research presented in this article offers significant insights into LUAD. The authors identified 113 PCDRGs that were differentially expressed in LUAD. These genes are implicated in various biological functions, including High risk ing apoptosis, ferroptosis, and pathways specific to non-small cell lung cancer. Notably, the PCDI proved effective in distinguishing between High risk and Low risk LUAD patients, demonstrating a higher accuracy in prognosis prediction compared to traditional clinical indicators such as age and gender. This high prediction accuracy was validated in both test and validation cohorts. Additionally, these genes showed significant correlations with immune cell infiltration and drug sensitivity in LUAD patients.ConclusionWe analysed the expression and function of PCDRGs in LUAD and revealed their correlation with patient survival, the immune microenvironment and drug sensitivity. The constructed PCDI model provides a scientific basis for the personalised treatment of lung adenocarcinoma, and future optimisation of treatment strategies based on these genes may improve patient clinical outcomes.

Trait association and prediction through integrative k-meranalysis.

Genome-wide association study (GWAS) with single nucleotide polymorphisms (SNPs) has been widely used to explore genetic controls of phenotypic traits. Alternatively, GWAS can use counts of substrings of length k from longer sequencing reads, k-mers, as genotyping data. Using maize cob and kernel color traits, we demonstrated that k-mer GWAS can effectively identify associated k-mers. Co-expression analysis of kernel color k-mers and genes directly found k-mers from known causal genes. Analyzing complex traits of kernel oil and leaf angle resulted in k-mers from both known and candidate genes. A gene encoding a MADS transcription factor was functionally validated by showing that ectopic expression of the gene led to less upright leaves. Evolution analysis revealed most k-mers positively correlated with kernel oil were strongly selected against in maize populations, while most k-mers for upright leaf angle were positively selected. In addition, genomic prediction of kernel oil, leaf angle, and flowering time using k-mer data resulted in a similarly high prediction accuracy to the standard SNP-based method. Collectively, we showed k-mer GWAS is a powerful approach for identifying trait-associated genetic elements. Further, our results demonstrated the bridging role of k-mers for data integration and functional gene discovery.

Discrimination of Explosive Residues by Standoff Sensing Using Anodic Aluminum Oxide Microcantilever Laser Absorption Spectroscopy with Kernel-Based Machine Learning.

Standoff laser absorption spectroscopy (LAS) has attracted considerable interest across many applications for environmental safety. Herein, we propose an anodic aluminum oxide (AAO) microcantilever LAS combined with machine learning (ML) for sensitive and selective standoff discrimination of explosive residues. A nanoporous AAO microcantilever with a thickness of <1 μm was fabricated using a micromachining process; its spring constant (18.95 mN/m) was approximately one-third of that of a typical Si microcantilever (53.41 mN/m) with the same dimensions. The standoff infrared (IR) spectra of pentaerythritol tetranitrate, cyclotrimethylene trinitramine, and trinitrotoluene were measured using our AAO microcantilever LAS over a wide range of wavelengths, and they closely matched the spectra obtained using standard Fourier transform infrared spectroscopy. The standoff IR spectra were fed into ML models, such as kernel extreme learning machines (KELMs), support vector machines (SVMs), random forest (RF), and backpropagation neural networks (BPNNs). Among these four ML models, the kernel-based ML models (KELM and SVM) were found to be efficient learning models able to satisfy both a high prediction accuracy (KELM: 94.4%, SVM: 95.8%) and short hyperparameter optimization time (KELM: 5.9 s, SVM: 7.6 s). Thus, the AAO microcantilever LAS with kernel-based learners could emerge as an efficient sensing method for safety monitoring.

The Impact of Prospect Theory on Asset Forecasting: A Comparative Study Based on Random Forest and Linear Regression

This study focuses on the application of predictive models and prospect theory in the field of machine learning to predict financial asset prices. Here, the linear regression and random forest algorithms were employed to forecast the price values and fluctuations of two different financial assets: the S&amp;P 500 index and Bitcoin prices. Meanwhile, this study compared the performance of different financial asset datasets before and after the introduction of prospect theory models. Through calculation and comparative analysis, this article provides an in-depth discussion on the predictive performance of regression models and classification models. The research results indicate that in most cases, simple linear regression models have high prediction accuracy. Meanwhile, this paper also found that introducing prospect theory can effectively improve the accuracy of prediction models for specific financial assets. This result has a positive impact on the financial industry, helping to optimize risk management and investment decision-making, improving efficiency at the market level and promoting information transparency, while also promoting the development of emerging financial formats in financial innovation

Dissecting transcriptome signals of anti-PD-1 response in lung adenocarcinoma

Immune checkpoint blockades are actively adopted in diverse cancer types including metastatic melanoma and lung cancer. Despite of durable response in 20–30% of patients, we still lack molecular markers that could predict the patient responses reliably before treatment. Here we present a composite model for predicting anti-PD-1 response based on tumor mutation burden (TMB) and transcriptome sequencing data of 85 lung adenocarcinoma (LUAD) patients who received anti-PD-(L)1 treatment. We found that TMB was a good predictor (AUC = 0.81) for PD-L1 negative patients (n = 20). For PD-L1 positive patients (n = 65), we built an ensemble model of 100 XGBoost learning machines where gene expression, gene set activities and cell type composition were used as input features. The transcriptome-based models showed excellent accuracy (AUC > 0.9) and highlighted the contribution of T cell activities. Importantly, nonresponder patients with high prediction score turned out to have high CTLA4 expression, which suggested that neoadjuvant CTLA4 combination therapy might be effective for these patients. Our data and analysis results provide valuable insights into developing biomarkers and strategies for treating LUAD patients using immune checkpoint inhibitors.

Genomic insights into mRNA COVID-19 vaccines efficacy: Linking genetic polymorphisms to waning immunity

ABSTRACT Genetic polymorphisms have been linked to the differential waning of vaccine-induced immunity against COVID-19 following vaccination. Despite this, evidence on the mechanisms behind this waning and its implications for vaccination policy remains limited. We hypothesize that specific gene variants may modulate the development of vaccine-initiated immunity, leading to impaired immune function. This study investigates genetic determinants influencing the sustainability of immunity post-mRNA vaccination through a genome-wide association study (GWAS). Utilizing a hospital-based, test negative case-control design, we enrolled 1,119 participants from the Taiwan Precision Medicine Initiative (TPMI) cohort, all of whom completed a full mRNA COVID-19 vaccination regimen and underwent PCR testing during the Omicron outbreak. Participants were classified into breakthrough and protected groups based on PCR results. Genetic samples were analyzed using SNP arrays with rigorous quality control. Cox regression identified significant single nucleotide polymorphisms (SNPs) associated with breakthrough infections, affecting 743 genes involved in processes such as antigenic protein translation, B cell activation, and T cell function. Key genes identified include CD247, TRPV1, MYH9, CCL16, and RPTOR, which are vital for immune responses. Polygenic risk score (PRS) analysis revealed that individuals with higher PRS are at greater risk of breakthrough infections post-vaccination, demonstrating a high predictability (AUC = 0.787) in validating population. This finding confirms the significant influence of genetic variations on the durability of immune responses and vaccine effectiveness. This study highlights the importance of considering genetic polymorphisms in evaluating vaccine-induced immunity and proposes potential personalized vaccination strategies by tailoring regimens to individual genetic profiles.

Development of a prognostic model for NSCLC based on differential genes in tumour stem cells

Non-small cell lung cancer (NSCLC) constitutes a significant portion of lung cancers and cytotoxic drugs (e.g. cisplatin) are currently the first-line treatment. However, NSCLC has developed resistance to this drug, which limits the therapeutic effect and thus affects prognosis. NSCLC sc-RNA-seq data were downloaded from the GEO database and Ku Leuven Laboratory for Functional Epigenetics, and bulk RNA-seq data were obtained from the TCGA database. The “Seurat” package was employed for scRNA-seq data processing, and the uniform manifold approximation and projection (UMAP) were applied for downscaling and cluster identification. Use the FindAllMarkers function to find differential genes (DEGs) for tumor stem cells. Then, we performed univariate regression analyses on the DEGs to identify potential prognostic genes. We created a machine learning framework based on potential prognostic genes, which combines 10 machine learning methods and their 101 combinations to get the optimal prognostic risk model. The model was evaluated in the training set and validation set. A nomogram was developed to provide physicians with a quantitative tool for prognosis prediction. Finally, we evaluated the expression and functionality of SLC2A1. We discovered 22 cell clusters containing 218379 cells by examining single-cell RNA sequencing datasets (GSE148071, KU_lom, GSE131907, GSE136246, GSE127465). Tumour cells were isolated for subpopulation analysis and 162 differential genes from SOX2_cancer were obtained. After univariate Cox analysis, we found 23 genes with prognostic potential prognostic value and utilized them to develop 101‑combination machine learning computational framework. We eventually picked the best performing ‘StepCox[both] + RSF’, which includes 8 genes. The model has a relatively high prediction accuracy in both TCGA and GEO datasets. In in vitro investigations, targeted suppression of the SLC2A1 gene resulted in significant reductions in proliferation, invasion and migration in A549 cells. In addition, a significant reduction in cisplatin resistance was seen in A549/DDP cells. The outcomes demonstrated the precision and credibility of the prognostic model for NSCLC, highlighting its potential significance in the treatment and prognosis of individuals affected by this disease. SLC2A1 may become a promising prognostic marker and a potential therapeutic target, offering valuable insights to inform clinical treatment decisions.

Quantitative prediction of water quality in Dongjiang Lake watershed based on LUCC

Land Use/ Cover Change (LUCC) plays a crucial role in influencing hydrological processes, nutrient cycling, and sediment transport in watersheds, ultimately impacting water quality on both spatial and temporal scales. Accurately predicting changes in watershed water quality is beneficial for the sustainable management of water resources. Current models often lack the ability to effectively predict water quality changes in a dynamic spatio-temporal context, particularly in complex watershed environments. The overall purpose of the study is to establish a comprehensive and dynamic modeling framework that links LUCC with water quality, allowing for accurate predictions of future water quality under varying land use scenarios. The model, which uses water quality as the dependent variable and LUCC as the independent variable, was developed to quantitatively predict changes in watershed water quality. To achieve this, annual multi-period remote sensing images from Landsat-5, Landsat-8 or Sentinel-2 satellites spanning from 1992 to 2022 were analyzed. Random Forest (achieving a Kappa coefficient of 0.9468) were employed to classify land use within the watershed. Based on classification results, a Cellular Automata-Markov chain model (CA-Markov) was constructed to simulate and predict the spatio-temporal patterns of land use, incorporating driving factors such as proximity to water systems, roads, elevation, and slope. Validation of the model using LUCC data from 2020 yielded a high prediction accuracy with a Kappa coefficient of 0.9505. The CA-Markov model was further utilized to project LUCC under three different scenarios—natural development, ecological protection, and arable land protection—between 2023 and 2033. Based on these projections, the coupled water quality and LUCC model was employed to predict water quality changes in the watershed over the same period. Key findings indicate that water quality is likely to improve under ecological protection scenario, while deterioration is expected under natural development scenario and cropland protection scenario due to urban expansion, agricultural practices, and water diversion for irrigation. This study provides a robust framework for watershed management, offering scientific guidance for source management and water purification efforts, thereby contributing significantly to the sustainable development of water resources.

PEZy-miner: An artificial intelligence driven approach for the discovery of plastic-degrading enzyme candidates

Plastic waste has caused a global environmental crisis. Biocatalytic depolymerization mediated by enzymes has emerged as an efficient and sustainable alternative for plastic treatment and recycling. However, it is challenging and time-consuming to discover novel plastic-degrading enzymes using conventional cultivation-based or omics methods. There is a growing interest in developing effective computational methods to identify new enzymes with desirable plastic degradation functionalities by exploring the ever-increasing databases of protein sequences. In this study, we designed an innovative machine learning-based framework, named PEZy-Miner, to mine for enzymes with high potential in degrading plastics of interest. Two datasets integrating information from experimentally verified enzymes and homologs with unknown plastic-degrading activity were created respectively, covering eleven types of plastic substrates. Protein language models and binary classification models were developed to predict enzymatic degradation of plastics along with confidence and uncertainty estimation. PEZy-Miner exhibited high prediction accuracy and stability when validated on experimentally verified enzymes. Furthermore, by masking the experimentally verified enzymes and blending them into homolog dataset, PEZy-Miner effectively concentrated the experimentally verified entries by 14∼30 times while shortlisting promising plastic-degrading enzyme candidates. We applied PEZy-Miner to 0.1 million putative sequences, out of which 27 new sequences were identified with high confidence. This study provided a new computational tool for mining and recommending promising new plastic-degrading enzymes.

Exploring novel MYH7 gene variants using in silico analyses in Korean patients with cardiomyopathy

BackgroundPathogenic variants of MYH7, which encodes the beta-myosin heavy chain protein, are major causes of dilated and hypertrophic cardiomyopathy.MethodsIn this study, we used whole-genome sequencing data to identify MYH7 variants in 397 patients with various cardiomyopathy subtypes who were participating in the National Project of Bio Big Data pilot study in Korea. We also performed in silico analyses to predict the pathogenicity of the novel variants, comparing them to known pathogenic missense variants.ResultsWe identified 27 MYH7 variants in 41 unrelated patients with cardiomyopathy, consisting of 20 previously known pathogenic/likely pathogenic variants, 2 variants of uncertain significance, and 5 novel variants. Notably, the pathogenic variants predominantly clustered within the myosin motor domain of MYH7. We confirmed that the novel identified variants could be pathogenic, as indicated by high prediction scores in the in silico analyses, including SIFT, Mutation Assessor, PROVEAN, PolyPhen-2, CADD, REVEL, MetaLR, MetaRNN, and MetaSVM. Furthermore, we assessed their damaging effects on protein dynamics and stability using DynaMut2 and Missense3D tools.ConclusionsOverall, our study identified the distribution of MYH7 variants among patients with cardiomyopathy in Korea, offering new insights for improved diagnosis by enriching the data on the pathogenicity of novel variants using in silico tools and evaluating the function and structural stability of the MYH7 protein.

Machine learning-driven prediction of phosphorus adsorption capacity of biochar: Insights for adsorbent design and process optimization

Phosphorus (P) pollution in aquatic environments poses significant environmental challenges, necessitating the development of effective remediation strategies, and biochar has emerged as a promising adsorbent for P removal at the cost of extensive research resources worldwide. In this study, a machine learning approach was proposed to simulate and predict the performance of biochar in removing P from water. A dataset consisting of 190 types of biochar was compiled from literature, encompassing various variables including biochar characteristics, water quality parameters, and operating conditions. Subsequently, the random forest and CatBoost algorithms were fine-tuned to establish a predictive model for P adsorption capacity. The results demonstrated that the optimized CatBoost model exhibited high prediction accuracy with an R2 value of 0.9573, and biochar dosage, initial P concentration in water, and C content in biochar were identified as the predominant factors. Furthermore, partial dependence analysis was employed to examine the impact of individual variables and interactions between two features, providing valuable insights for adsorbent design and operating condition optimization. This work presented a comprehensive framework for applying a machine learning approach to address environmental issues and provided a valuable tool for advancing the design and implementation of biochar-based water treatment systems.

An evolutionary deep learning model based on XGBoost feature selection and Gaussian data augmentation for AQI prediction

Accurate prediction of air quality is crucial for ensuring the scientific validity and effectiveness of air pollution control measures. This study proposes a combined deep learning (DL) model (XGBoost-GDA-TCN-IMRFO-GRU) for predicting hourly air quality index (AQI) data in four cities. The model integrates Extreme gradient boosting (XGBoost) for feature selection, Gaussian data augmentation (GDA), improved manta ray foraging optimization (IMRFO) algorithm, temporal convolutional network (TCN), and gated recurrent unit (GRU). XGBoost calculates the scores of pollutant gases affecting AQI, selecting the top four important pollutants (PM2.5, PM10, NO2, O3) based on their importance rankings. GDA enhances the robustness of the DL models and addresses the limitations of insufficient and overfitting training datasets. Additionally, the IMRFO algorithm, with two improved strategies, is applied to enhance the GRU model. TCN extracts spatiotemporal features of AQI, while GRU constructs a temporal model for efficient computations. Compared to eleven benchmark models, the proposed model demonstrates superior performance in terms of MAE, RMSE, MAPE, and NSE, achieving high accuracy and optimal prediction performance. Specifically, the XGBoost-GDA-TCN-IMRFO-GRU model reduces RMSE, MAE, and MAPE by 33–60 %, 39–68 %, and 39–66 %, respectively, compared to the TCN model. Therefore, the XGBoost-GDA-TCN-IMRFO-GRU model can provide reliable early warnings for air quality, which is of great significance for air pollution prevention and the sustainable development of society.

Stacking integrated learning-based inverse design of four-nanopore high-Q all-dielectric metasurface

In this paper, we establish a four-nanophole hollowed out all-dielectric metasurface structure as the object of reverse design, which can realize many types of high Q-value Fano resonance effects through dynamic tuning of a single structure, with Q value up to 4401. We used the time domain finite difference method for data collection, and then select appropriate models according to the characteristics of the data from the perspective of the data itself. We select in small sample prediction excellent support vector regression (SVR), gradient promotion decision tree (GBDT), prediction generalization performance and stability of high random forest (RF) as a base learners, with good nonlinear fitting ability BP neural network (BPNN) yuan learners, establish a fusion model based on Stacking integrated learning strategy. Based on this fusion model, the multi-parameter all-dielectric metasurface structure is reverse designed instead. The results show that the proposed method has high prediction accuracy with an absolute average error of only 0.0043, and excellent average accuracy of 82.5%, 77.9% and 14% compared with the combined model GBDT-SVM-BP, GBDT-RF-BP, and RF-SVM-BP. This study provides a new perspective on the reverse design of all-dielectric metasurface structures.

Analysing Urban Traffic Patterns with Neural Networks and COVID-19 Response Data

Accurate traffic prediction is crucial for urban planning, especially in rapidly growing cities. Traditional models often struggle to account for sudden traffic pattern changes, such as those caused by the COVID-19 pandemic. Neural networks offer a powerful solution, capturing complex, non-linear relationships in traffic data for more precise prediction. This study aims to create a neural network model for predicting vehicle numbers at main intersections in the city. The model is created using real data from the sensors placed across the city of Zilina, Slovakia. By integrating pandemic-related variables, the model assesses the COVID-19 impact on traffic flow. The model was developed using neural networks, following the data-mining methodology CRISP-DM. Before the modelling, the data underwent thorough preparation, emphasising correcting sensor errors caused by communication failures. The model demonstrated high prediction accuracy, with correlations between predicted and actual values ranging from 0.70 to 0.95 for individual sensors and vehicle types. The results highlighted a significant pandemic impact on urban mobility. The model’s adaptability allows for easy retraining for different conditions or cities, making it a robust, adaptable tool for future urban planning and traffic management. It offers valuable insights into pandemic-induced traffic changes and can enhance post-pandemic urban mobility analysis.

Prediction of resilient modulus and critical dynamic stress of recycled aggregates: Experimental study and machine learning methods

This paper aimed to investigate the feasibility of partially or completely replacing natural aggregates with recycled aggregates from construction and demolition wastes for low-carbon-emission use as coarse-grained embankment fill materials. The laboratory specimens were prepared by blending natural and recycled aggregates at varying proportions, and a series of laboratory repeated load triaxial compression tests were carried out to study the effects of material index properties and dynamic stress states on the resilient modulus and permanent strain characteristics. Based on the experimental results and by considering the main influencing parameters of the resilient modulus and permanent deformation, an artificial neural network (ANN) prediction model with optimal architecture was developed and optimized by the particle swarm optimization (PSO) algorithm, and its performance and accuracy were verified by supplementary analyses. A shakedown state classification method was proposed based on the unsupervised clustering algorithm, and a prediction model of critical dynamic stress was established based on the machine learning (ML) method and the shakedown state classification results. The research results indicate that the stress state has a greater influence on the resilient modulus and permanent deformation characteristics than other factors, and the shear stress ratio has a significant effect on the shakedown state. The resilient modulus and critical dynamic stress of such specimens vary linearly with confining pressure. The improved PSO-ANN prediction model exhibits high prediction accuracy and robustness, superior to several other commonly used ML regression prediction algorithms. The resilient modulus and critical dynamic stress prediction methods based on ML algorithms can provide technical guidance and theoretical basis for the design and in-service maintenance of similar unbound granular materials.

High-Level Feature Fusion Deep Learning Model for Fault Detection in Handling Equipment in Dry Bulk Ports

The flexibility of handling equipment in dry bulk ports is poor, and frequent equipment fault induced by the high-load and high-power working conditions greatly impacts the overall port handling operations, making accurate fault detection play an important role in improving the efficiency and stability of dry bulk port operations. However, as we know, most fault detection methods for port handling equipment depend heavily on monitoring sensor data, which is not applicable in the dry bulk port due to high configuration and maintenance cost, as well as the high false alarm rate of monitoring sensors caused by strong background noise. To solve the problem, this study proposes a High-Level Feature Fusion Deep Learning Model, which uses different deep learning sub-models to extract features of structured and unstructured data. It fuses the extracted feature vectors to achieve fault detection in the handling equipment, establishing the mapping relationship between the fault (e.g., waiting for the pre-loading process, equipment fault, and others) and multi-source heterogeneous operation and maintenance data for the handling equipment, including reclaimers, belt conveyors, dumpers, and ship loaders. To verify the effectiveness of the proposed method, the actual data of a coal port in Northern China is employed as an example. The results show the deep learning model can achieve high prediction accuracy (over 86%) with high efficiency (0.5 s for each sample), which provides decision support for the fault detection in dry bulk port handling equipment.

Bridging Structure- and Ligand-Based Virtual Screening through Fragmented Interaction Fingerprint.

Ligand-based virtual screening (LBVS) and structure-based virtual screening (SBVS), and their combinations, are frequently conducted in modern drug discovery campaigns. As a form of combination, an amalgamation of methods from ligand- and structure-based information, termed hybrid VS approaches, has been extensively investigated such as using interaction fingerprints (IFPs) in combination with machine learning (ML) models. This approach has the potential to prioritize active compounds in terms of protein-ligand binding and ligand structural characteristics, which is assumed to be difficult using either one of the approaches. Herein, we present an IFP, named the fragmented interaction fingerprint (FIFI), for hybrid VS approaches. FIFI is constructed from the extended connectivity fingerprint atom environments of a ligand proximal to the protein residues in the binding site. Each unique ligand substructure within each amino acid residue is encoded as a bit in FIFI while retaining sequence order. From the retrospective evaluation of activity prediction using a limited number and variety of active compounds for six biological targets, FIFI consistently showed higher prediction accuracy than that using previously proposed IFPs. For the same data sets, the screening performance of LBVS, SBVS sequential VS, parallel VS, and other hybrid VS approaches was investigated. Compared to these approaches, FIFI in combination with ML showed overall stable and high prediction accuracy, except for one target: the kappa opioid receptor, where the extended connectivity fingerprint combined with ML models showed better performance than other approaches by wide margins.