Prediction Accuracy Rate Research Articles

CTITF: A tensor factorization model with constrained bidirectional user trust and implicit feedback for context-aware recommender systems

Recommender systems offer an efficient solution to the problem of information overload, which is exacerbated by the rapid expansion of data. Context-aware recommender systems (CARS) have become prominent, incorporating contextual information to provide more desirable recommendations. While the dimension of contextual information rises, the complexity of algorithms increases as well, highlighting the data sparsity problem. In this paper, we propose CTITF, a novel tensor factorization model that incorporates constrained user bidirectional trust and implicit feedback. First, CTITF distinguishes the roles of trust networks in terms of the directionality of trust relationships: the trustor and the trustee. CTITF then constructs trust influences and biases for both roles to linearly represent user preferences. Furthermore, CTITF improves the rating prediction function and recommendation objective function based on CP factorization. Finally, CTITF filters out trust relationships where users do not have the same history items. It also uses contextual information to limit the amount of implicit feedback, addressing the issue of high time complexity. Experiments on two real-world datasets illustrate that the proposed model outperforms previous TF-based models and social recommender systems in terms of rating prediction accuracy. In addition, the CTITF model reduces the training time by 50.28% compared to the trustTF model, which also uses trust.

Genome-wide association study and genomic selection of flax powdery mildew in Xinjiang Province.

Flax powdery mildew (PM), caused by Oidium lini, is a globally distributed fungal disease of flax, and seriously impairs its yield and quality. To data, only three resistance genes and a few putative quantitative trait loci (QTL) have been reported for flax PM resistance. To dissect the resistance mechanism against PM and identify resistant genetic regions, based on four years of phenotypic datasets (2017, 2019 to 2021), a genome-wide association study (GWAS) was performed on 200 flax core accessions using 674,074 SNPs and 7 models. A total of 434 unique quantitative trait nucleotides (QTNs) associated with 331 QTL were detected. Sixty-four loci shared in at least two datasets were found to be significant in haplotype analyses, and 20 of these sites were shared by multiple models. Simultaneously, a large-effect locus (qDI 11.2) was detected repeatedly, which was present in the mapping study of flax pasmo resistance loci. Oil flax had more QTL with positive-effect or favorable alleles (PQTL) and showed higher PM resistance than fiber flax, indicating that effects of these QTL were mainly additive. Furthermore, an excellent resistant variety C120 was identified and can be used to promote planting. Based on 331 QTLs identified through GWAS and the statistical model GBLUP, a genomic selection (GS) model related to flax PM resistance was constructed, and the prediction accuracy rate was 0.96. Our results provide valuable insights into the genetic basis of resistance and contribute to the advancement of breeding programs.

Isolation forest-voting fusion-multioutput: A stroke risk classification method based on the multidimensional output of abnormal sample detection

Background and ObjectiveStroke has become a major disease threatening the health of people around the world. It has the characteristics of high incidence, high fatality, and a high recurrence rate. At this stage, problems such as poor recognition accuracy of stroke screening based on electronic medical records and insufficient recognition of stroke risk levels exist. These problems occur because of the systematic errors of medical equipment and the characteristics of the collectors during the process of electronic medical record collection. Errors can also occur due to misreporting or underreporting by the collection personnel and the strong subjectivity of the evaluation indicators. MethodsThis paper proposes an isolation forest-voting fusion-multioutput algorithm model. First, the screening data are collected for numerical processing and normalization. The composite feature score index of this paper is used to analyze the importance of risk factors, and then, the isolation forest is used. The algorithm detects abnormal samples, uses the voting fusion algorithm proposed in this article to perform decision fusion prediction classification, and outputs multidimensional (risk factor importance score, abnormal sample label, risk level classification, and stroke prediction) results that can be used as auxiliary decision information by doctors and medical staff. ResultsThe isolation forest-voting fusion-multioutput algorithm proposed in this article has five categories (zero risk, low risk, high risk, ischemic stroke (TIA), and hemorrhagic stroke (HE)). The average accuracy rate of stroke prediction reached 79.59 %. ConclusionsThe isolation forest-voting fusion-multioutput algorithm model proposed in this paper can not only accurately identify the various categories of stroke risk levels and stroke prediction but can also output multidimensional auxiliary decision-making information to help medical staff make decisions, thereby greatly improving the screening efficiency.

Exploiting Rating Prediction Certainty for Recommendation Formulation in Collaborative Filtering

Collaborative filtering is a popular recommender system (RecSys) method that produces rating prediction values for products by combining the ratings that close users have already given to the same products. Afterwards, the products that achieve the highest prediction values are recommended to the user. However, as expected, prediction estimation may contain errors, which, in the case of RecSys, will lead to either not recommending a product that the user would actually like (i.e., purchase, watch, or listen) or to recommending a product that the user would not like, with both cases leading to degraded recommendation quality. Especially in the latter case, the RecSys would be deemed unreliable. In this work, we design and develop a recommendation algorithm that considers both the rating prediction values and the prediction confidence, derived from features associated with rating prediction accuracy in collaborative filtering. The presented algorithm is based on the rationale that it is preferable to recommend an item with a slightly lower prediction value, if that prediction seems to be certain and safe, over another that has a higher value but of lower certainty. The proposed algorithm prevents low-confidence rating predictions from being included in recommendations, ensuring the recommendation quality and reliability of the RecSys.

Machine learning-based prediction model for disc cutter life in TBM excavation through hard rock formations

Replacing damaged or worn disc cutters is costly and time-consuming, which can significantly reduce the utilization and advance rate of tunnel boring machines (TBMs). Accurate prediction of disc cutter life is crucial for optimizing TBM operation in tunneling projects. This study introduces a machine-learning-based prediction model designed to forecast disc cutter wear, incorporating the analysis of each cutter’s travel length and the intervals between cutterhead interventions (CHI). The principle underlying the developed machine learning approach involves usage of multiple learning algorithms, ensemble learning methods, and a sophisticated analysis of these factors to identify patterns and relationships essential for effectively predicting wear rates. Employing CHI report data from the Daegok–Sosa tunneling project’s hard rock excavation, the model evaluates 15 wear-influencing factors, providing precise wear predictions. This study proposes the ensemble machine learning (ML) methods, namely Random Forest (RF) and Extreme Gradient Boosting (XGB), for accurate wear rate predictions and discern influential factors. The proposed model demonstrated exceptional prediction accuracy, as evidenced by a root mean square error of 0.049 mm for a single-ring excavation length. Notably, this model innovatively accounts for variable wear rates of cutters based on the individual cutter travel lengths as well as other geological and operational parameters. Furthermore, the predicted cutter consumption rate showed reasonable correspondence when compared to the actual CHI records. The proposed model is expected to improve existing disc cutter life prediction methods and reduce the cost and time for replacing damaged or worn disc cutters.

Generalizability of polygenic prediction models: how is theR2defined on test data?

Polygenic risk scores (PRS) quantify an individual's genetic predisposition for different traits and are expected to play an increasingly important role in personalized medicine. A crucial challenge in clinical practice is the generalizability and transferability of PRS models to populations with different ancestries. When assessing the generalizability of PRS models for continuous traits, the is a commonly used measure to evaluate prediction accuracy. While the is a well-defined goodness-of-fit measure for statistical linear models, there exist different definitions for its application on test data, which complicates interpretation and comparison of results. Based on large-scale genotype data from the UK Biobank, we compare three definitions of the on test data for evaluating the generalizability of PRS models to different populations. Polygenic models for several phenotypes, including height, BMI and lipoproteinA, are derived based on training data with European ancestry using state-of-the-art regression methods and are evaluated on various test populations with different ancestries. Our analysis shows that the choice of the definition can lead to considerably different results on test data, making the comparison of values from the literature problematic. While the definition as the squared correlation between predicted and observed phenotypes solely addresses the discriminative performance and always yields values between 0 and 1, definitions of the based on the mean squared prediction error(MSPE) with reference to intercept-only models assess both discrimination and calibration. These MSPE-based definitions can yield negative values indicating miscalibrated predictions for out-of-target populations. We argue that the choice of the most appropriate definition depends on the aim of PRS analysis - whether it primarily serves for risk stratification or also for individual phenotype prediction. Moreover, both correlation-based and MSPE-based definitions of can provide valuable complementary information. Awareness of the different definitions of the on test data is necessary to facilitate the reporting and interpretation of results on PRS generalizability. It is recommended to explicitly state which definition was used when reporting values on test data. Further research is warranted to develop and evaluate well-calibrated polygenic models for diverse populations.

Prediction of treatment response after stereotactic radiosurgery of brain metastasis using deep learning and radiomics on longitudinal MRI data

We developed artificial intelligence models to predict the brain metastasis (BM) treatment response after stereotactic radiosurgery (SRS) using longitudinal magnetic resonance imaging (MRI) data and evaluated prediction accuracy changes according to the number of sequential MRI scans. We included four sequential MRI scans for 194 patients with BM and 369 target lesions for the Developmental dataset. The data were randomly split (8:2 ratio) for training and testing. For external validation, 172 MRI scans from 43 patients with BM and 62 target lesions were additionally enrolled. The maximum axial diameter (Dmax), radiomics, and deep learning (DL) models were generated for comparison. We evaluated the simple convolutional neural network (CNN) model and a gated recurrent unit (Conv-GRU)-based CNN model in the DL arm. The Conv-GRU model performed superior to the simple CNN models. For both datasets, the area under the curve (AUC) was significantly higher for the two-dimensional (2D) Conv-GRU model than for the 3D Conv-GRU, Dmax, and radiomics models. The accuracy of the 2D Conv-GRU model increased with the number of follow-up studies. In conclusion, using longitudinal MRI data, the 2D Conv-GRU model outperformed all other models in predicting the treatment response after SRS of BM.

Causality-aware social recommender system with network homophily informed multi-treatment confounders

Typical recommender systems utilize observed ratings of users as inputs to learn their preferences and aim to output recommendations of new items that users will like by predicting their potential ratings. The real world is driven by causality given that whether or not a user is made exposed to the item may significantly affect the rating. While some recent methods have taken a causal view to mitigate the confounding bias in observed rating data, few have recognized recommendation as a multiple causal inference problem that concerns numerous items simultaneously in practice. By framing the recommendation as a multiple causal inference problem, this paper develops a causality-aware social recommender that incorporates underlying social network structures with matrix factorization methods for deconfounding in networked observational data to enhance social recommendations. Leveraging social network information, which inherently confounds with the preferences of users, is particularly crucial but not trivial for inferring unobserved confounders in social recommender systems. Considering that connected users in a social network share similar attributes, we propose to incorporate the network homophily into the matrix factorization models through regularization to better learn the latent variables. The extracted latent variables then capture the network informed multi-treatment confounders to mitigate the confounding bias and improve the rating prediction accuracy. The models are estimated through a proximal gradient-based optimization framework, which not only eases the incorporation of the network structure constraints but also improves the computational efficiency of the proposed method. Simulation and case studies are conducted to validate the proposed method.

Predicting Indian GDP with Machine Learning: A Comparison of Regression Models

In recent years, the application of machine learning algorithms in economic forecasting has gained significant traction. This study focuses on predicting the Gross Domestic Product (GDP) of India by harnessing advanced machine learning techniques. We assembled a comprehensive dataset incorporating time series analysis and inflation rates from diverse sources. Our investigation involved a comparative analysis employing both linear and polynomial regression methods to discern the most accurate predictive model. Our findings underscore the superiority of the polynomial regression model, which excelled in capturing non-linear relationships between independent variables and GDP. Specifically, the polynomial regression model achieved an impressive prediction accuracy rate of surpassing the accuracy achieved by the linear regression model. This study underscores the critical role of advanced machine learning algorithms in economic forecasting. By emphasizing the significance of high-quality datasets and the application of techniques like polynomial regression, we illustrate how these factors can substantially enhance the precision of economic forecasts. These insights hold substantial implications for policy makers and businesses alike, aiding informed decision-making and effective economic policy development. This study serves as a valuable reference for future research, highlighting the importance of advanced machine learning methods and robust data sources in economic forecasting.

A peridynamic-informed deep learning model for brittle damage prediction

Physics-informed Neural Network (PINN) has been introduced recently to predict and understand complex physical phenomena by directly incorporating feedback from governing equations. While PINNs offer remarkable capabilities, challenges arise when addressing discontinuities and heterogeneity, potentially compromising accuracy and reliability in prediction outcomes. In this study, a novel approach that combines the principles of peridynamic (PD) theory with PINN is presented to predict quasi-static damage and crack propagation in brittle materials. To achieve high prediction accuracy and convergence rate, the linearized PD governing equation is enforced in the PINN’s residual-based loss function. The proposed PD-INN is able to learn and capture complicated displacement patterns associated with different geometrical parameters, such as pre-crack position and length. The computational method presented in this study can be implemented to any PD constitutive model like Bond-Based PD or State-Based PD as well as any horizon factor. Several enhancements like cyclical annealing schedule and deformation gradient aware optimization technique are proposed to ensure the model would not get stuck in its trivial solution. The model’s performance assessment is conducted by monitoring the behavior of loss function throughout the training process. The results obtained through PD-INN demonstrate a satisfactory level of agreement in 2D and 3D when compared with the ground truth deformation from high-fidelity techniques like PD direct numerical method and Extended finite element method (X-FEM). Our results show the ability of the nonlocal PD-INN to predict damage and crack propagation accurately and efficiently.

Application Study on the Reinforcement Learning Strategies in the Network Awareness Risk Perception and Prevention

The intricacy of wireless network ecosystems and Internet of Things (IoT) connected devices have increased rapidly as technology advances and cyber threats increase. The existing methods cannot make sequential decisions in complex network environments, particularly in scenarios with partial observability and non-stationarity. Network awareness monitors and comprehends the network's assets, vulnerabilities, and ongoing activities in real-time. Advanced analytics, machine learning algorithms, and artificial intelligence are used to improve risk perception by analyzing massive amounts of information, identifying trends, and anticipating future security breaches. Hence, this study suggests the Deep Reinforcement Learning-assisted Network Awareness Risk Perception and Prevention Model (DRL-NARPP) for detecting malicious activity in cybersecurity. The proposed system begins with the concept of network awareness, which uses DRL algorithms to constantly monitor and evaluate the condition of the network in terms of factors like asset configurations, traffic patterns, and vulnerabilities. DRL provides autonomous learning and adaptation to changing network settings, revealing the ever-changing nature of network awareness risks in real time. Incorporating DRL into risk perception increases the system's capacity to recognize advanced attack methods while simultaneously decreasing the number of false positives and enhancing the reliability of risk assessments. DRL algorithms drive dynamic and context-aware response mechanisms, making up the adaptive network prevention component of the development. Predicting new threats and proactively deploying preventive measures, such as changing firewall rules, isolating compromised devices, or dynamically reallocating resources to reduce developing risks, is made possible by the system's ability to learn from historical data and prevailing network activity. The suggested DRL-NARPP model increases the anomaly detection rate by 98.3%, the attack prediction accuracy rate by 97.4%, and the network risk assessment ratio by 96.4%, reducing the false positive ratio by 11.2% compared to other popular methodologies.

Exploring Investment Optimization and “Greenwashing” from ESG Disclosure: A Dual Examination of Investor Perception

This study investigates the intricate correlation between environmental, social, and governance (ESG) information and the financial performance of companies, with a focus on the fundamental nature of ESG and its influence on the choices made by investors. This study examines available literature and data analysis to uncover how disclosing ESG information impacts investment optimization. Additionally, it clarifies the relationship between greenwashing and the advancement of green financial products. The study employs the XGBoost ensemble learning method, using non-financial features of ESG combined with financial features to construct a prediction model, achieving a prediction accuracy rate of 71.26%. Furthermore, applying this model aims to further utilize it in stock selection and constructing a stock pool. By analyzing the financial performance of companies predicted by the model, we will select potential high-performance stocks to build an investment portfolio. Then, we use the Markowitz portfolio theory to optimize the weight combination of stocks in the pool to maximize expected returns and minimize risk. After backtesting the investment portfolio using the closing prices in 2021, its annualized return was a positive 5.76%, significantly higher than the benchmark portfolio. Additionally, this study provides theoretical references and practical guidance for insight and addressing the potential large-scale greenwashing behavior under the trend of increasing ESG information disclosure in the future.

Impact of downstream obstructions on ogee weir efficiency: a regression analysis

ABSTRACT This study delves into the impact of downstream obstruction angles on the discharge coefficient (Cd) over ogee weirs within open channel flows, a critical factor for accurate flow rate predictions in hydraulic engineering. Employing a series of detailed laboratory experiments, the influence of various obstruction angles on Cd was scrutinized applying a suite of regression analysis to develop predictive models. The analysis was enriched by considering hydraulic parameters such as flow rate, water level, and weir geometry. Despite the established importance of Cd in hydraulic designs the nuanced effects of downstream obstructions have received limited attention, highlighting a critical research gap. The findings highlight a strong correlation between obstruction angles and Cd, with developed regression models demonstrating notable predictive strength. Remarkably the models exhibited varying levels of accuracy, with the Random Forest regressor achieving an exceptionally low root mean square error (RMSE) of 0.005, indicating superior predictive performance. Conversely, traditional models like Decision tree and XG BOOST reflected higher RMSE values of 0.60, suggesting less predictive accuracy in this context. LASSO, Bayesian Ridge, and OMP regressors stood out with an RMSE of zero, denoting perfect predictions under the study's specific conditions.

Study protocol for a scoping review of Lyme disease prediction methodologies

IntroductionIn the temperate world, Lyme disease (LD) is the most common vector-borne disease affecting humans. In North America, LD surveillance and research have revealed an increasing territorial expansion of hosts,...

Comparison of Novel Proteomic Expression Profiles for Radiation Exposure in Male and Female C57BL6 Mice.

There is a need for point-of-care diagnostics for future mass casualty events involving radiation exposure. The development of radiation exposure and dose prediction algorithms for biodosimetry is needed for screening of large populations during these scenarios, and exploration of the potential effects which sex, age, genetic heterogeneity, and physiological comorbidities may have on the utility of biodosimetry diagnostics is needed. In the current study, proteomic profiling was used to examine sex-specific differences in age-matched C57BL6 mice on the blood proteome after radiation exposure, and the usefulness of development and application of biodosimetry algorithms using both male and female samples. Male and female mice between 9-11 weeks of age received a dose of total-body irradiation (TBI) of either 2, 4 or 8 Gy and plasma was collected at days 1, 3 and 7 postirradiation. Plasma was then screened using the SomaScan v4.1 assay for ∼7,000 protein analytes. A subset panel of protein biomarkers demonstrated significant (FDR < 0.05 and |logFC| > 0.2) changes in expression after radiation exposure. All proteins were used for feature selection to build predictive models of radiation exposure using different sample and sex-specific cohorts. Both binary (prediction of any radiation exposure) and multidose (prediction of specific radiation dose) model series were developed using either female and male samples combined or only female or only male samples. The binary series (models 1, 2 and 3) and multidose series (models 4, 5 and 6) included female/male combined, female only and male only respectively. Detectable values were obtained for all ∼7,000 proteins included in the SomaScan assay for all samples. Each model algorithm built using a unique sample cohort was validated with a training set of samples and tested with a separate new sample series. Overall predictive accuracies in the binary model series was ∼100% at the model training level, and when tested with fresh samples, 97.9% for model 1 (female and male) and 100% for model 2 (female only) and model 3 (male only). When sex-specific models 2 and 3 were tested with the opposite sex, the overall predictive accuracy rate dropped to 62.5% for model 2 and remained 100% for model 3. The overall predictive accuracy rate in the multidose model series was 100% for all models at the model training level and, when tested with fresh samples, 83.3%, 75% and 83.3% for Multidose models 4-6, respectively. When sex-specific model 5 (female only) and model 6 (male only) were tested with the opposite sex, the overall predictive accuracy rate dropped to 52.1% and 68.8%, respectively. These models represent novel predictive panels of radiation-responsive proteomic biomarkers and illustrate the utility and necessity of considering sex-specific differences in development of radiation biodosimetry prediction algorithms. As sex-specific differences were observed in this study, and as use of point-of-care radiation diagnostics in future mass casualty settings will necessarily include persons of both sexes, consideration of sex-specific variation is essential to ensure these diagnostic tools have practical utility in the field.

Hyperspectral Imaging and Machine Learning as a Nondestructive Method for Proso Millet Seed Detection and Classification.

Millet is a small-seeded cereal crop with big potential. There are many different cultivars of proso millet (Panicum miliaceum L.) with different characteristics, bringing forth the issue of sorting which are important for growers, processors, and consumers. Current methods of grain cultivar detection and classification are subjective, destructive, and time-consuming. Therefore, there is a need to develop nondestructive methods for sorting the cultivars of proso millet. In this study, the feasibility of using near-infrared (NIR) hyperspectral imaging (900-1700 nm) to discriminate between different cultivars of proso millet seeds was evaluated. A total of 5000 proso millet seeds were randomly obtained and investigated from the ten most popular cultivars in the United States, namely Cerise, Cope, Earlybird, Huntsman, Minco, Plateau, Rise, Snowbird, Sunrise, and Sunup. To reduce the large dimensionality of the hyperspectral imaging, principal component analysis (PCA) was applied, and the first two principal components were used as spectral features for building the classification models because they had the largest variance. The classification performance showed prediction accuracy rates as high as 99% for classifying the different cultivars of proso millet using a Gradient tree boosting ensemble machine learning algorithm. Moreover, the classification was successfully performed using only 15 and 5 selected spectral features (wavelengths), with an accuracy of 98.14% and 97.6%, respectively. The overall results indicate that NIR hyperspectral imaging could be used as a rapid and nondestructive method for the classification of proso millet seeds.

An Ultra-Short-Term Wind Power Prediction Method Based on Quadratic Decomposition and Multi-Objective Optimization

To augment the accuracy, stability, and qualification rate of wind power prediction, thereby fostering the secure and economical operation of wind farms, a method predicated on quadratic decomposition and multi-objective optimization for ultra-short-term wind power prediction is proposed. Initially, the original wind power signal is decomposed using a quadratic decomposition method constituted by the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Fuzzy Entropy (FE), and Symplectic Geometry Mode Decomposition (SGMD), thereby mitigating the randomness and volatility of the original signal. Subsequently, the decomposed signal components are introduced into the Deep Bidirectional Long Short-Term Memory (DBiLSTM) neural network for time series modeling, and the Sand Cat Swarm Optimization Algorithm (SCSO) is employed to optimize the network hyperparameters, thereby enhancing the network’s predictive performance. Ultimately, a multi-objective optimization loss that accommodates accuracy, stability, and grid compliance is proposed to guide network training. Experimental results reveal that the employed quadratic decomposition method and the proposed multi-objective optimization loss can effectively bolster the model’s predictive performance. Compared to other classical methods, the proposed method achieves optimal results across different seasons, thereby demonstrating robust practicality.

Analyzing energy performance in American low income households: A DataDriven approach with machine learning insights

The energy burden within low-income households presents a significant societal challenge that necessitates a thorough understanding for developing effective and sustainable policies. However, very few studies analyze and model energy-related factors among low-income individuals. Thus, this study critically investigates the relationship between various buildings' characteristics and four distinct energy-related outputs (i.e., energy burden, annual energy cost, annual energy cost per square footage, and annual energy cost per square footage per person) for both low-income and non-low-income households across the United States, using six machine learning algorithms. Leveraging the American Housing Survey dataset, this study identifies factors impacting energy burden and consumption and highlights variables contributing to the energy burden disparity among these two household groups, compromising census division, number of floors within the unit, household income, federal poverty level threshold, and number of rooms in the unit for non-low-income households, and the number of persons aged 18 and over, census division, household income, number of rooms in a unit, and unit size in square feet for low-income households. Additionally, it introduces 48 models to predict energy-related outputs and evaluates the accuracy of models. To evaluate the accuracy of these models, two key metrics are employed: R2 (coefficient of determination) and RMSE (root mean square error), which provide insights into the models’ predictive accuracy and error rates, respectively. The study reveals that Gradient Boosting Regression and XGBoost predict outcomes for low-income and non-low-income households with higher accuracy and with fewer inputs, making them cost-effective and efficient models. The findings enhance our understanding of energy equity issues and equip policymakers with actionable insights to alleviate energy burden disparities and promote energy equity across diverse socioeconomic landscapes.

Genetic characteristics and ancestry inference ability analyses of 57 InDel loci in Hezhou Han population

Abstract The Han nationality is widely distributed in different regions, and it is one of the most populous ethnic groups in China. Han individuals dwelled in Guangxi as a part of Chinese Han population have relatively less research than minorities who live in Guangxi Zhuang Autonomous Region. In this study, the genetic polymorphisms of 57 autosomes InDel loci were explored in Hezhou Han (HZH) population. Forensic-related parameters revealed that these 57 InDel loci had high forensic validities, and they could be used in forensic practice research. In addition, the genetic relationships between the HZH population and 30 worldwide reference populations were explored using a variety of analytical methods such as phylogenetic tree, principal component analyses and structure analyses, and the results demonstrated that there were closer genetic relationships between the HZH and nine populations of East Asia. The prediction accuracy rate of five inter-continental cross-validation analyses for individuals from East Asia were higher than 0.9, and the prediction accuracy rate of three inter-continental cross-validation analyses for individuals from East Asia, Europe and Africa were all greater than 0.95. In addition, 24 of the 57 InDel loci were ancestral inferred loci that could well distinguish individuals of East Asia, Europe and Africa. In conclusion, these loci could be used not only as a good tool for individual identification and paternity testing in HZH population, but also as an auxiliary tool for ancestry inference studies.

Digital Twin-Driven Multi-Factor Production Capacity Prediction for Discrete Manufacturing Workshop

Traditional capacity forecasting algorithms lack effective data interaction, leading to a disconnection between the actual plan and production. This paper discusses the multi-factor model based on a discrete manufacturing workshop and proposes a digital twin-driven discrete manufacturing workshop capacity prediction method. Firstly, this paper gives a system framework for production capacity prediction in discrete manufacturing workshops based on digital twins. Then, a mathematical model is described for discrete manufacturing workshop production capacity under multiple disturbance factors. Furthermore, an innovative production capacity prediction method, using the “digital twin + Long-Short-Term Memory Network (LSTM) algorithm”, is presented. Finally, a discrete manufacturing workshop twin platform is deployed using a commemorative disk custom production line as the prototype platform. The verification shows that the proposed method can achieve a prediction accuracy rate of 91.8% for production line capacity. By integrating the optimization feedback function of the digital twin system into the production process control, this paper enables an accurate perception of the current state and future changes in the production system, effectively evaluating the production capacity and delivery date of discrete manufacturing workshops.