Decision Tree Model Research Articles

An accelerated deterministic algorithm for maximizing monotone submodular minus modular function with cardinality constraint

Submodular optimization not only covers some classical combinatorial optimization problems, but also has a wide range of applications in fields such as machine learning and artificial intelligence. For submodular maximization problems with constraints, some work has been done including the design of approximation algorithms, the measurement of approximation algorithms in terms of quality and efficiency, etc. In this paper, we consider the problem of maximizing a non-negative monotone submodular function minus a non-negative modular function with the cardinality constraint. This model has been applied to many scenarios, such as team formation problem, influence maximization problem, recommender systems problem, etc. We propose a threshold algorithm that achieve a (1/2−O(ε),2)-bicriteria approximation ratio and query complexity O(nlog⁡n). Our algorithm makes a small sacrifice in the approximation ratio but improves the best query complexity result of existing deterministic algorithms from O(n2) to O(nlog⁡n) in the worst case.

Low-velocity impact response of hybrid core sandwich panels with spring and strut cores filled with resin, silicone, and foam

Advancements in the load-bearing capacity of composite panels open doors to high-performance applications. The integration of additive manufacturing allows for the creation of intricate core designs effortlessly. Hybrid cores, combining structural elements with infill materials, play a crucial role in enhancing panel impact resistance while maintaining its low weight. This study compares sandwich panels incorporating spring and octet strut structural elements infused with different materials—silicon, foam, and epoxy resin—evaluating their energy absorption capabilities. Additive manufacturing is employed to produce these panels with structural elements then subsequently filled with infills. The drop tower test is utilized to experimentally assess panel behavior under low-velocity impact. Design of experiments and statistical analysis are used to examine the influence of core height, impact height, core geometry, and filling type on the damaged area and impactor penetration. Results showed that the strut-based structure performed better than other structures in preventing penetration, with a damaged area reduction from 501.45 to 301.58 m2 compared to the spring core. The addition of foam or silicon reduced the impact damage to the front and the back sheets, with silicon infills proving to be the most effective, reducing penetration by reducing penetration by about 60%. The depth of impact was measured, with results indicating that the truss core displayed the smallest specific depth of penetration. A decision tree model predicted that a sandwich panel with a spring core would have a 100% chance of perforation while a filled core showed a significantly reduced penetration risk.

Visual deterioration outcomes following optic pathway glioma treatment: a 12-year single institution retrospective study.

The surgical treatment of optic pathway gliomas (OPG) remains controversial, with visual outcomes often unpredictable. The present study explored surgical and clinical factors influencing visual acuity (VA) after OPG treatment and developed anatomical subtypes correlated with clinical symptoms. Children with OPG who underwent initial partial tumor resection at Beijing Tiantan Hospital from January 2011 to December 2022 were retrospectively analyzed. Multivariate logistic regression and random forest analyses were performed to identify risk factors for post-treatment VA deterioration and a decision tree model was created based on significant factors. A total of 140 patients were enrolled. Multivariate logistic regression analysis identified surgical approach and initial VA as independent predictors of post-treatment VA deterioration (P < 0.05). Surgical approach, initial VA, and extent of tumor resection were the most significant factors for risk assessment and were included in the decision tree model, with surgical approach as the most important "root" node. The model demonstrated good predictive performance, with area under the curve values of 0.75 and 0.66 for the training and test datasets, respectively. A simple anatomical classification was developed, which revealed clinical characteristic differences among OPG types. Meanwhile, a correlation analysis of post-treatment visual deterioration was performed for each of the three anatomical types. This study offers a predictive model for visual outcomes following initial tumor-reduction surgery in OPG patients, which may help in visual outcomes risk stratification. Additionally, the anatomical classification effectively indicates OPG growth direction, offering potential insights into clinical symptoms.

Explainable machine learning for assessing upper respiratory tract of racehorses from endoscopy videos

Laryngeal hemiplegia (LH) is a major upper respiratory tract (URT) complication in racehorses. Endoscopy imaging of horse throat is a gold standard for URT assessment. However, current manual assessment faces several challenges, stemming from the poor quality of endoscopy videos and subjectivity of manual grading. To overcome such limitations, we propose an explainable machine learning (ML)-based solution for efficient URT assessment. Specifically, a cascaded YOLOv8 architecture is utilized to segment the key semantic regions and landmarks per frame. Several spatiotemporal features are then extracted from key landmarks points and fed to a decision tree (DT) model to classify LH as Grade 1,2,3 or 4 denoting absence of LH, mild, moderate, and severe LH, respectively. The proposed method, validated through 5-fold cross-validation on 107 videos, showed promising performance in classifying different LH grades with 100%, 91.18%, 94.74% and 100% sensitivity values for Grade 1 to 4, respectively. Further validation on an external dataset of 72 cases confirmed its generalization capability with 90%, 80.95%, 100%, and 100% sensitivity values for Grade 1 to 4, respectively. We introduced several explainability related assessment functions, including: (i) visualization of YOLOv8 output to detect landmark estimation errors which can affect the final classification, (ii) time-series visualization to assess video quality, and (iii) backtracking of the DT output to identify borderline cases. We incorporated domain knowledge (e.g., veterinarian diagnostic procedures) into the proposed ML framework. This provides an assistive tool with clinical-relevance and explainability that can ease and speed up the URT assessment by veterinarians.

Molecular simulations and deep neural networks‐based interpretable machine learning modelling of reverse adsorptive MOFs for ethane/ethylene separation

AbstractThe thermal decomposition of ethane (C2H6) and the steam cracking of fossil fuels are the main sources of ethylene (C2H4). However, it usually contains 5%–9% of C2H6 residue, which must be reduced to ensure its utilization during polymerization. C2H6 and C2H4 have comparable kinetic diameters and boiling points (C2H6: 4.44, 184.55 K; C2H4: 4.16, 169.42 K), which makes the separation process very difficult. This contribution employs a methodology that integrates machine learning (ML) with Monte Carlo simulations to evaluate the ddmof database to develop a predictive model for separating ethane (C2H6) and ethylene (C2H4). The ML model's input is the metal–organic frameworks (MOFs) chemical and structural descriptors. The grand canonical Monte Carlo (GCMC) simulations in RASPA software were carried out to calculate the equilibrium adsorption of ethane and ethylene. Different ML models such as random forest, decision tree, and deep neural network models have been tested to estimate the selectivity and ethane uptake from the MOF data being generated. Interpretable ML model using SHapley Additive exPlanations (SHAP) is developed for the better understanding of the impact of the parameters on selectivity and ethane uptake. A user‐friendly graphical user interface (GUI) is presented, allowing users to predict the ethane uptake and selectivity of MOFs simply by entering the values of chemical and structural descriptors.

Revalidation of the applicability of Altmetrics indicators in article-level evaluation: An empirical analysis of papers of different types of citation trajectories

While providers try to control the quality of the data, the applicability of Altmetrics indicators to the assessment of scientific papers remains an open question. One important reason is that the citation counts used to explain and evaluate the applicability of Altmetrics in this regard do not directly and completely reflect the impact and quality of papers. In view of the fact that the introduction of citation trajectory helps to enrich our understanding of the impact and quality of papers, this study first discusses the correlation between citation counts and Altmetrics indicators of papers under different citation trajectory types on the basis of dividing five citation trajectory types and considering possible influences such as field and publication year. Then, after controlling the relevant variables, we construct a multinomial logistic regression with the citation trajectory type as the dependent variable to analyze the possible relationship between Altmetrics and the citation trajectory type of papers. Finally, we construct a decision tree model and a regression model after mixed sampling to verify the robustness of the regression results. The findings reveal that there were significant differences in the performance of Altmetrics indicators among papers with different citation trajectory types. The applicability of Altmetrics for evaluating papers with different citation trajectory types should be judged carefully. At the same time, it is suggested that robust Altmetrics (such as save) can be applied to assess the quality of papers and characterize the citation life cycle.

Thirty years’ spatio-temporal evolution of desertification degrees and driving factors in Turpan–Hami Basin, Xinjiang, China

Turpan-Hami (Tuha) Basin is in an extremely arid area, surrounded by mountains and desert with sparse vegetation. It has experienced serious desertification over the past 30 years, resulting in ecological environment and socio-economic issues. To reveal the temporal and spatial evolutions of desertification degrees in Tuha Basin, we first constructed an evaluation system for the desertification degree classification using vegetation and soil-related indices; then long-time series Landsat 5 TM/ Landsat8 OLI images and a C5.0 decision tree (DT) model were used to monitor large-scale desertification from 1990 to 2020. We applied a geographic detector to discover the driving forces between desertification changes and natural and human factors. The results demonstrated that the severe desertification (SD) accounted for the largest desertification degree, and the transitions of various desertification degrees mainly occurred between extremely severe desertification (ESD) and SD, which were considered the most active degrees. Only 9.4 % of Tuha Basin showed an expansion trend in desertification degree, with the most significant expansion occurred in 1990–1995. The proportion of 13.6 % desertification showed a reversion trend, with the most significant reversion occurred in 1995–2010. The main driving factors affecting the evolution of desertification degrees were precipitation and temperature, with the average q value higher than 0.95. Human activity factors such as year-end cropland area and population also impacted the patterns of desertification degree, with the q values of 0.9 and 0.7, respectively. The interactive detection enhanced the driving forces and the interaction between precipitation and other factors played a leading role in desertification degree changes. The results provide scientific data and a basis for desertification control and ecological protection in arid areas.

Exploring the mechanism of path-creating strategy for latecomers: a combined approach of econometrics and causal machine learning

In this paper, the traditional econometrics method and causal machine-learning method are combined to study the mechanism of a path-creating strategy of latecomers to influence latecomers’ catch-up performance. A total of 283 high-tech manufacturing enterprises listed on the Shanghai and Shenzhen stock exchanges from 2007 to 2019 were selected for the study. OLS linear regression model verifies that path-creating has a positive impact on latecomers’ technological catch-up performance, technological capability plays an intermediary role between path-creating and technology catch-up performance, technological innovation appropriability positively moderates the effect of path-creating on technological capability, and technological innovation cumulativeness negatively moderates the effect of path-creating on technological catch-up but positively moderate the effect of technological capability on catch-up performance. Through machine learning, on the one hand, a conclusion basically consistent with the linear regression model is obtained, but on the other hand, a more heterogeneous situation is presented. Through analyses of the individual treatment effect of a path-creating strategy of latecomers, the Shapley value graph shows the complex influence of different features on the treatment effect of the enterprise using the path-creating strategy. Through the decision tree, some more complex patterns are found. In addition, the decision tree model based on causal analysis can also assist enterprises in making strategic decisions.

Cost-effectiveness of Azvudine for High-risk Outpatients with Mild-to-moderate Coronavirus Disease 2019 in China

PurposeThis study aimed to evaluate the cost-effectiveness of Azvudine for the treatment of mild-to-moderate coronavirus disease 2019 in high-risk outpatients using real-world data and relevant references. MethodsIn the decision-tree model, 2 cohorts were organized in a single center to compare the cost-effectiveness between the Azvudine plus symptomatic treatment group and the symptomatic treatment group. We calculated the cost and mortality rate for both groups. The incremental cost-effectiveness ratio was used to illustrate the cost-effectiveness. To assess the uncertainty of the model parameters, we conducted 1-way and probabilistic sensitivity analyses. FindingsIn total, there were 804 outpatients included in the model. Among these, 317 patients received Azvudine plus symptomatic treatment, whereas the remaining 487 participants were treated with symptomatic treatment alone. The costs in the Azvudine and control groups were 1055.48 yuan and 2466.97 yuan and the survival rates were 100.00% and 98.70%, respectively. After calculation, the incremental cost-effectiveness ratio was determined to be −108,817.48 yuan per person. In the section of 1-way and probabilistic sensitivity analyses, Azvudine was still proven to be cost-effective. ImplicationsOur results support the usage of Azvudine for the treatment of high-risk outpatients with mild-to-moderate coronavirus disease 2019 from economic perspective.

Development of a Predictive Model to Determine Appropriate Length of Profile.

Musculoskeletal injuries are one of the primary causes of Soldiers' inability to be medically ready, comprising over 80% of such causes. The electronic profile (e-Profile) is the way that musculoskeletal injuries are documented so that commanders will know the type of injury as well as the length of the time that the Soldier will need limited duty. A previous study of e-Profiles in an Army MTF Integrated Pain Management Center showed that the median length of an e-Profile was 30 days. It is in the best interest of the Army to have the Soldier out of the fight the minimum amount of time for recovery to ensure the unit readiness. The goal of this study was to utilize e-Profile data to see if a machine learning model can be developed to determine the appropriate time a Soldier needs to be on profile for a given diagnoses. Institutional Review Board approval was obtained from the USAMRDC (protocol #M-10966). The initial dataset provided to the research team consisted of a single pipe delimited ("|") text file containing 2.9 million rows of e-Profile data. Linear regression, decision trees, and random forests (RFs) were evaluated to see which model would best predict the number of days needed for an e-Profile. Linear regression had an adjusted R-squared of 0.165. The positive predictive value of decision trees (0-to-30-day range of e-Profiles) was 73.6%, and the negative predictive value (30-90 days) was 60.9% with an area under the receiver operating characteristic curve (AUC) of 0.694 for the model. The positive predictive value of RFs was 85.3% (for the 0-30 range), and the negative predictive value was 58.7% (for the 30-90 range) with an AUC of 0.794. An AUC that approaches 1 indicates a more accurate prediction. The 3 models (linear regression, decision trees, and RF) studied as part of this project did not predict the days on e-Profile with a high degree of certainty. Future research will focus on adding additional data to the e-Profile dataset in order to improve model accuracy.

Advancing nanomedicine production via green method: Modeling and simulation of pharmaceutical solubility at different temperatures and pressures

This study employs machine learning algorithms to model the mole fraction of paracetamol drug and the density of supercritical CO2 as a solvent. The tree-based models were employed to evaluate the impact of temperature and pressure on the fluctuations in drug solubility. The dataset utilized in this study has two input variables: temperature and pressure. Conversely, two factors were regarded as outputs: the solubility of drug and the density of solvent. To model the mole fraction and density, Gaussian Process Regression (GPR), Decision Tree (DT), and Linear Regression (LR) models were trained by some collected experimental data. These models were boosted with AdaBoost algorithm to enhance performance. The Firework Algorithm (FWA) was used to optimize the models’ hyper-parameters. All models performed well in predicting both outputs, but outcomes demonstrated that the ADA-GPR model, with R2 values of 0.995 and 0.996, respectively, achieved the highest accuracy for predicting both mole fraction and density. Also, the Explained Variance Scores of this model are 0.995 and 0.998 for mole fraction and density, respectively.

Flashlight model: Integrating attention distribution and attention resources for pilots’ visual behaviour analysis and performance prediction

Pilot performance is almost the last line of defense in aircraft safety. Recent years have seen a surge in research aimed at utilizing eye-tracking technology to predict pilot performance, enhancing aviation safety margins. A decline in pilot performance is often attributed to either misdirected attention towards irrelevant tasks or inefficient information processing owing to limited attention resources. Previous research has shown that eye-tracking data can effectively capture these issues and provide accurate performance predictions. Nevertheless, the existing studies either focus on attention distribution or attention resources separately, neglecting the complex interactions between them. To address this gap, our study proposes a synthesized Flashlight model-based eye-tracking analysis for pilot performance prediction, integrating the two perspectives. Accordingly, the combined AOI-gaze metrics are proposed to offer a more nuanced analysis of information processing across specific Areas of Interest (AOIs), thereby enhancing the analysis of gaze metrics. We examined the efficacy of the combined AOI-gaze metrics in the Gradient-boosted decision trees(GBDT) model for pilot performance prediction and compared them with other widely used eye-tracking metrics in a simulated flight experiment case study. Moreover, we employed the SHapley Additive exPlanations (SHAP) method to identify the most influential eye-tracking measurements for pilots’ performance prediction. The result demonstrated that the selected eye-tracking measurements obtained the highest accuracy in performance prediction.

Research on non-destructive identification technology of rice varieties based on HSI and GBDT

Accurate identification of rice varieties is of great significance for rice planting, field management and storage, and is also a key link in the process of agricultural breeding. In this study, a gradient boosting decision tree (GBDT) model was established based on hyperspectral imaging (HSI) to realize high-speed and non-destructive variety identification of six rice varieties. In this study, the near-infrared hyperspectral images of 600 rice samples of 6 varieties were taken as the research object, and the characteristic spectra of sensitive regions of the sample spectral images were processed by multiplicative scatter correction (MSC), and after the characteristic wavelengths were determined by the importance scores, the GBDT model to realize the identification of rice sample varieties, and the grid search algorithm was used to optimize the four internal parameters of GBDT. The results showed that the established GBDT model for the accuracy of rice variety identification of vitro test set samples reached 95%, indicating that HSI can be used to quickly and non-destructively identify rice varieties, and provide a new idea for batch online non-destructive testing of rice seeds.

Estimation of Greenhouse Gas Emissions of Taxis and the Nonlinear Influence of Built Environment Considering Spatiotemporal Heterogeneity

The fuel consumption and greenhouse gas (GHG) emission patterns of taxis are in accordance with the urban structure and daily travel footprints of residents. With taxi trajectory data from the intelligent transportation system in Xi’an, China, this study excludes trajectories from electric taxis to accurately estimate GHG emissions of taxis. A gradient boosting decision tree (GBDT) model is employed to examine the nonlinear influence of the built environment (BE) on the GHG emissions of taxis on weekdays and weekends in various urban areas. The research findings indicate that the GHG emissions of taxis within the research area exhibit peak levels during the time intervals of 7:00–9:00, 12:00–14:00, and 23:00–0:00, with notably higher emission factors on weekends than on weekdays. Moreover, a clear nonlinear association exists between BE elements and GHG emissions, with a distinct impact threshold. In the different urban areas, the factors that influence emissions exhibit spatial and temporal heterogeneity. Metro/bus/taxi stops density, residential density, and road network density are the most influential BE elements impacting GHG emissions. Road network density has both positive and negative influences on the GHG emissions in various urban areas. Increasing the road network density in subcentral urban areas and increasing the mixed degree of urban functions in newly developed urban centers to 1.85 or higher can help reduce GHG emissions. These findings provide valuable insights for reducing emissions in urban transportation and promoting sustainable urban development by adjusting urban functional areas.

Machine learning-based predictive approach for pitting and uniform corrosion in geothermal energy systems

Geothermal energy is a sustainable source from Earth's crust, and holds great potential for electricity generation, but corrosion poses a significant challenge. In this study, we employed a range of machine learning models, including linear regression, decision tree, k-nearest neighbors, random forest, and support vector regression to predict uniform and pitting corrosion. Despite limited data performance issues, virtual samples from a synthetic data generator improved results when combined with actual data. Fine-tuning with various hyperparameters enhanced model performance, with the decision tree proving the most effective. Exhaustive feature selection identifies key factors influencing uniform and pitting corrosion, validated by the models.

Do green innovation and governance limit CO2 emissions: evidence from twelve polluting countries with panel data decision tree model

We examine the effectiveness of green innovation on CO2 emissions in the top twelve polluting nations—China, the US, India, Russia, Japan, South Korea, Canada, Mexico, Turkey, Italy, Poland, and the UK—from 1996 to 2020. Using panel data fixed and random effect model and decision tree analysis, we found that industrialization, urbanization, and economic growth increase CO2 emissions, whereas green energy consumption and governance decrease CO2 emissions. In the panel data tree-based model, governance is in the second and third positions in the decision tree fixed, and random effect model. Green innovation is not statistically significant despite the expected negative sign. The findings suggest that policymakers should encourage investment in green energy production and governance to combat environmental degradation. Investment in green energy should be escalated to ensure energy efficiency in the long term.

SSF-CDW: achieving scalable, secure, and fast OLAP query for encrypted cloud data warehouse

Implementing a cloud-based data warehouse to store sensitive or critical strategic data presents challenges primarily related to the security of the stored information and the exchange of OLAP queries between the cloud server and users. Although encryption is a viable solution for safeguarding outsourced data, applying it to OLAP queries involving multidimensional data, measures, and Multidimensional Expressions (MDX) operations on encrypted data poses difficulties. Existing searchable encryption solutions are inadequate for handling such complex queries, which complicates the use of business intelligence tools that rely on efficient and secure data processing and analysis.This paper proposes a new privacy-preserving cloud data warehouse scheme called SSF-CDW which facilitates a secure and scalable solution for an encrypted cloud data warehouse. Our SSF-CDW improves the OLAP queries accessible only to authorized users who can decrypt the query results with improved query performance compared to traditional OLAP tools. The approach involves utilizing symmetric encryption and Ciphertext Policy Attribute-Based Encryption (CP-ABE) to protect the privacy of the dimension and fact data modeled in Multidimensional OLAP (MOLAP). To support efficient OLAP query execution, we proposed a new data cube retrieval mechanism using a Redis schema which is an in-memory database. This technique dynamically compiles queries by disassembling them down into multiple levels and consolidates the results mapped to the corresponding encrypted data cube. The caching of dimensional and fact data associated with the encrypted cube is also implemented to improve the speed of frequently queried data. Experimental comparisons between our proposed indexed search strategy and other indexing schemes demonstrate that our approach surpasses alternative techniques in terms of search speed for both ad-hoc and repeated OLAP queries, all while preserving the privacy of the query results.

Major Depressive Disorder with Catatonia: A Phenotype Related to Autistic Traits and High Suicidality.

Background: Major Depressive Disorder (MDD) represents a significant global health concern, often complicated by comorbidities such as catatonia and autism spectrum disorder (ASD). Recognizing the interplay among these conditions and their impact on suicidal tendencies is crucial for effective clinical management. Methods: A total sample of 147 subjects with MDD was divided into Significant Catatonia (SC) and Non-Significant Catatonia (NSC) groups based on Catatonia Spectrum (CS) scores. Participants were evaluated through the Structured Clinical Interview for DSM-5, Research Version (SCID-5-RV), the Adult Autism Subtreshold Spectrum (AdAS Spectrum), and the Mood Spectrum-Self Report questionnaires. Statistical analyses included Mann-Whitney U test, Chi-square test, logistic regression analyses, and a decision tree model. Results: The SC group exhibited higher CS, AdAS Spectrum, and MOODS-SR total and domain scores compared to the NSC group. Individuals with significant autistic traits were over-represented in the SC group, as well as participants with higher suicidality, suicidal ideation, and a history of suicide attempts. The total AdAS Spectrum and MOOD-SR score, the AdAS domain "Hyper-hypo reactivity to sensory input", and the "Cognitive depressive" MOOD-SR domain were predictive of belonging to the SC group. Suicidality levels appeared to be higher in clinically significant ASD, intermediate in subjects with autistic traits (AT), and low in the absence of AT. Conclusions: the study suggests the existence of a specific phenotype of MDD associated with catatonia, characterized by elevated autistic traits and suicide risk.

Analyzing key health factors influencing life expectancy using machine learning

With the rapid development of global medical technology and the steady improvement of social living standards, life expectancy per capita has become one of the most important indicators of a country or region's level of development. It not only reflects the quality of life and health of the local people, but also profoundly affects the economic growth and social stability of the country. In underdeveloped countries, life expectancy at birth is generally lower than in more developed countries due to resource constraints and poor medical facilities. This phenomenon has triggered extensive research interest in whether there is some correlation between life expectancy per capita and economic growth, and how improving life expectancy can contribute to a country's economic transformation and development. The purpose of this paper is to explore the impact of life expectancy per capita on economic growth and how to promote the economic transformation and development of countries by increasing life expectancy. Through a comparative study of Asian countries such as China, Singapore and Japan, this paper analyzes the impact of different factors on life expectancy through technical methods such as visual analysis, hypothesis testing, regression modeling, and decision tree modeling, and explores how these factors play a role in economic growth. The results of this study may have some guiding significance for improving life expectancy.

Diagnose Breast Cancer Using Two Machine Learning Methods andComparing and Analyzing Them

The breast cancer is currently the number one cancer in the world and has a high early treatment rate. Therefore, early screening and diagnosis of breast cancer is very important. Machine learning is very strong in analyzing and processing massive data. In this paper, we train and optimize decision tree and SVM models to identify malignant breast cancer and compare and analyze the performance of the two models. The accuracy of the earliest optimized models reaches about 98%, and it is found that the two models focus on different classification effects for the two samples, which can be further optimized by stacking and other ways. The dataset used to train the models in this paper is from the Wisconsin breast cancer database (WBCD), a benchmark dataset commonly used to compare different algorithms, which is of some significance for exploring the use of machine learning in the field of medical diagnosis.