Tree Algorithm Research Articles

AI CARDIOLOGIST ADVANCEMENTS IN SUPERVISED LEARNING FOR HEART DISEASE PREDICTION

Heart disease is the biggest problem in the world and having no age to occur it can occur to a man or even a kid or any healthy person with the problems in their genes. Early and accurate prediction is crucial for effective preventive measures. This project explores the transformative potential of supervised learning within Artificial Intelligence (AI) for heart disease prediction. We used many algorithms like KNN and Tree algorithm to study more about the disease-predicting technology. The project examines how AI cardiologists, by using the algorithms can able to take the data of the user or a patient and can help the patient to get a review of the disease and the stage they were in, This type of analysis holds trust for more accurate and personalized risk assessments, leading that resulted in data to get a new outcome on how to prevent the problem. We understand all of the challenges of data quality, bias mitigation, and explainability in AI models, emphasizing the importance of ethical considerations in their development and deployment. Finally, the paper discusses the future directions of AI-powered heart disease prediction, exploring the potential of emerging techniques like explainable AI and federated learning to advance this field further. Keywords: Cardiovascular disease (CVD) prediction, Supervised learning, Artificial Intelligence (AI), Heart disease, Algorithms (logistic regression, support vector machine)

Digital soil mapping of soil subgroup class information in Coimbatore district using decision tree approach

The study aimed to evaluate the effectiveness of Digital Soil Mapping (DSM) compared to traditional soil mapping methods, which can help implementing precise near-real-time smart agricultural applications. Conventional soil surveys, while informative, often lack detail and are labour-intensive. DSM addresses these limitations by integrating soil data with environmental covariates and classification algorithms. Four hundred forty soil profile data points were collected from various sources and grouped according to the USDA Soil Taxonomy at the soil subgroup level. Utilizing Landsat 8 satellite data and 33 environmental covariates, the decision tree algorithm generated 56 rules to predict soil classes. Key influencing factors identified include agro-climatic zones, physiography, mean annual minimum temperature, the green wavelength region of spectral data, rainfall, and geology. The model was trained on 348 data points and validated on 92 data points, achieving a classification accuracy of 79.35% and a Kappa coefficient of 0.78, indicating high reliability. The study concludes that DSM is a viable alternative to conventional soil mapping methods, primarily using decision tree algorithms. It demonstrates that the accuracy of DSM can be significantly enhanced by incorporating a larger number of soil profile observations and relevant environmental covariates. The expert system approach provides a more detailed and up-to-date understanding of soil distribution, crucial for agricultural planning and natural resource management in the Coimbatore district, Western Tamil Nadu.

Prediction and risk assessment of stress corrosion failures of prestressed anchors in underground mines

ABSTRACT Stress corrosion cracking (SCC) in deep underground anchor systems presents a growing threat to mining infrastructure integrity, driven by extreme environmental corrosion coupled with mechanical stress. To anticipate the progression of stress corrosion in deep anchor bolts, this study establishes a machine learning framework integrating 12 critical corrosion-influencing features with optimised support vector machine (SVM) modelling. The corrosion data collected regarding bolt failures in underground conditions furnished valuable references for the relevant research. The rigorous data cleaning methodologies are employed to refine the raw data sourced from anchoring materials. The statistical and machine learning models are utilised to execute data imputation and normalisation, facilitating the establishment of an SVM model tailored specifically for anchor material corrosion prediction. To enhance the predictive capabilities of the SVM algorithm, the model was optimised through the integration of principal component analysis and gradient boosting tree algorithms. The high accuracy of the model in predicting bolt corrosion risk was verified, and the weight of influences of environmental factors on corrosion failure are analysed. Key mechanistic insights reveal that stress and drip water flow rate dominate corrosion progression through synergistic electrochemical-stress interactions. The validated framework provides mine operators with a decision-support tool for proactive maintenance planning and corrosion-resistant anchoring system design in extreme environments.

Geospatial costs and emissions assessment of universal Fiber-To-The-Neighborhood (FTTnb) broadband infrastructure strategies for Sub-Saharan Africa

Abstract Currently, fixed fiber infrastructure is essential for providing universal broadband but has received relatively little research attention in low-income countries compared to other more cost-efficient wireless technologies. Yet, pushing out fiber broadband network to local areas is essential, even if the final access network is still wireless. Here, we design least-cost Fiber-To-The-Neighborhood (FTTnb) architectures using two spatial optimization Steiner Tree algorithms to jointly determine investment costs, environmental emissions, and Social Carbon Costs. We find that the average annualized per user emissions in low population density areas (<9 people per km2) range from 1.9 kg CO2 e and 9.6 kg CO2 e, compared to 0.02kg CO2 e and 0.12 kg CO2 e for high population density areas (>958 people per km2). Moreover, Total Cost of Ownership for building fiber closer to premises is approximately US$ 2.1 billion in high population density areas (>958 people per km2) compared to US$ 64 billion for sparsely populated regions (<21 people per km2). The findings suggest that building a fiber closer to premises in sparsely populated areas will cost 3.1% of the GDP of Sub-Saharan Africa. Moreover, the total emissions from building FTTnb will account for 0.16-0.85% of the region’s cross-sector greenhouse gas emissions. Thus, 48% (about 550 million) of the total Sub-Saharan African population live in areas where FTTnb is viable within the next ten years.

Determination of Health Needs of Earthquake Victims with Non-Communicable Diseases.

This study aimed to determine the health needs of individuals with non-communicable diseases affected by earthquakes. The study employed a descriptive and cross-sectional design and was conducted in 3 of the 11 provinces affected by the February 6, 2023 earthquakes. Data were obtained using an introductory information form and a health needs information form. Percentages, averages, McNemar's test, and classification and regression tree algorithm for decision tree analysis were used to evaluate the data. Among the participants, 34.87% had hypertension, 27.95% had diabetes, and 14.12% had asthma. Compared to the pre-earthquake period, the participants' needs for medication, transportation to hospital, disease-specific nutrition, and social support significantly increased after the earthquake (P<0.05). This study revealed that participants with faced challenges in accessing the medicines, hospitals, medical devices, and disease-specific nutrition required for disease management during the early post-earthquake period, experiencing delays or no access. Among the identified health needs, participants with hypertension and diabetes require access to healthy nutrition, while those with asthma have a heightened need for clean air. Conducting health screenings in tent cities without requiring individual attendance at health tents and promptly identifying and addressing health needs in the early period are strongly recommended.

Achieving precision assessment of functional clinical scores for upper extremity using IMU-Based wearable devices and deep learning methods

Stroke is a serious cerebrovascular disease, and rehabilitation following the acute phase is particularly crucial. Not all rehabilitation outcomes are favorable, highlighting the necessity for personalized rehabilitation. Precision assessment is essential for tailored rehabilitation interventions. Wearable inertial measurement units (IMUs) and deep learning approaches have been effectively employed for motor function prediction. This study aims to use machine learning techniques and data collected from IMUs to assess the Fugl-Meyer upper extremity subscale for post-stroke patients with motor dysfunction. IMUs signals from 120 patients were collected during a clinical trial. These signals were fed into a gated recurrent unit network to complete the scoring of individual actions, which were then aggregated to obtain the total score. Simultaneously, on the basis of the internal correlation between the Fugl–Meyer assessment and the Brunnstrom scale, Brunnstrom stage prediction models of the arm and hand were established via the random forest and extremely randomized trees algorithm. The experimental results show that the proposed models can score Fugl-Meyer items with a high accuracy of 92.66%. The R2 between the doctors’ score and the model’s score is 0.9838. The Brunnstrom stage prediction models can predict high-quality stages, achieving a Spearman correlation coefficient of 0.9709. The application of the proposed method enables precision assessment of patients’ upper extremity motor function, thereby facilitating more personalized rehabilitation programs to achieve optimal recovery outcomes.Trial registration: Clinical trial of telerehabilitation training and intelligent evaluation system, ChiCTR2200061310, Registered 20 June 2022-Retrospective registration.

Application of DCE-MRI radiomics and heterogeneity analysis in predicting luminal and non-luminal subtypes of breast cancer

PurposeThe aim of this study was to explore the application value of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics and heterogeneity analysis in the differentiation of molecular subtypes of luminal and non-luminal breast cancer.MethodsIn this retrospective study, 388 female breast cancer patients (48.37 ± 9.41 years) with luminal (n = 190) and non-luminal (n = 198) molecular subtypes who received surgical treatment at Jilin Cancer Hospital were recruited from January 2019 to June 2023. All patients underwent breast MRI scan and DCE scan before surgery. The patients were then divided into a training set (n = 272) and a validation set (n = 116) in a 7:3 ratio. The three-dimensional texture feature parameters of the breast lesion areas were extracted. Four tumor heterogeneity parameters, including type I curve proportion, type II curve proportion, type III curve proportion and tumor heterogeneity values were calculated and normalized. Five machine learning (ML) models, including the logistic regression, naive Bayes algorithm (NB), k-nearest neighbor (KNN), decision tree algorithm (DT) and extreme gradient boosting (XGBoost) model were used to process the training data and were further validated. The best ML model was selected according to the performance in the validation set.ResultsIn luminal subtype breast lesions, type III curve proportion and heterogeneity index were significantly lower than the corresponding parameters of the non-luminal subtype lesions both in the training set and validation set. Eight features together with four heterogeneity-related parameters with significant differences between luminal and non-luminal groups were retained as radiomics signatures for constructing the prediction model. The logistic regression ML model achieved the best performance in the validation set with the highest area under the curve value (0.93), highest accuracy (86.94%), sensitivity (87.55%) and specificity (86.25%).ConclusionThe radiomics and heterogeneity analysis based on the DCE-MRI exhibit good application value in discriminating luminal and non-luminal subtype breast cancer. The logistic regression model demonstrates the best predictive performance among various machine learning models.

A Method for Identifying Landslide-Prone Areas Using Multiple Factors and Adaptive Probability Thresholds: A Case Study in Northern Tongren, Longwu River Basin, Qinghai Province

Early and accurate identification of landslide-prone areas is critical for monitoring and early-warning systems, forming the foundation of disaster prevention and mitigation. However, current landslide susceptibility assessment methods often rely on arbitrary probability classification thresholds, leading to subjective and regionally non-adaptive results that neglect low-susceptibility areas, thereby limiting their practical utility in disaster management. To address these limitations, this study proposes a novel method for identifying landslide-prone areas by integrating multi-factor analysis with adaptive probability thresholds. The methodology combines landslide catalog data with key landslide influencing factors, including geology, topography, precipitation, surface deformation, and human activities. The gradient boosting decision tree (GBDT) algorithm is employed to estimate landslide susceptibility probabilities, while an adaptive threshold criterion—based on minimizing the Jensen–Shannon (JS) divergences weighted sum between landslide-prone areas and positive samples—is established to objectively classify regions. Validation experiments were conducted in the northern Tongren region of the Longwu River Basin, Qinghai Province, China. Historical landslides (February 2016–June 2017) were used for model training, and subsequent landslides (June 2017–November 2022) served as validation data. The results demonstrate exceptional performance: the susceptibility model achieved an AUC value of 0.99, with 94.07% accuracy in classifying landslides positive samples. Furthermore, 77.78% of post-2017 landslides occurred within the identified prone areas, yielding a 22.22% omission rate. These findings highlight the method’s ability to dynamically adapt to regional characteristics, balance sensitivity and specificity, and provide actionable insights for landslide risk management.

Proportionally Fair Matching via Randomized Rounding

Given an edge-colored graph, the goal of the proportional fair matching problem is to find a maximum weight matching while ensuring proportional representation (with respect to the number of edges) of each color. The colors may correspond to demographic groups or other protected traits where we seek to ensure roughly equal representation from each group. It is known that, assuming ETH, it is impossible to approximate the problem with ℓ colors in time subexponential in ℓ even on unweighted path graphs. Further, even determining the existence of a non-empty matching satisfying proportionality is NP-Hard. To overcome this hardness, we relax the stringent proportional fairness constraints to a probabilistic notion. We introduce a notion we call δ-PʀᴏʙᴀʙʟʏFᴀɪʀ where we ensure proportionality up to a factor of at most (1 ± δ) for some small δ &gt; 0 with high probability. The violation δ can be brought arbitrarily close to 0 for some good instances with large values of matching size. We propose and analyze simple and fast algorithms for bipartite graphs that achieve constant-factor approximation guarantees, and return a δ-PʀᴏʙᴀʙʟʏFᴀɪʀ matching.

IOS-RAFS: Intelligent Opponent Selection Training Framework via Fuzzy Logic-based Switching between “Rule-AI” Dual Strategy Libraries

In recent years, reinforcement learning-based aerial combat strategy design has shown significant advantages in decision-making efficiency and flexibility. However, improper opponent strategy selection during training may hinder the agent’s ability to handle diverse and complex scenarios, reducing the generalization and performance of its strategies. To address this, this paper proposes “IOS-RAFS”, a framework that dynamically adjusts opponent levels at different stages to provide a more diverse and adaptive environment. In the IOS-RAFS training framework, IOS refers to intelligent opponent selection, RA represents the “Rule-AI” dual strategy libraries, which are established to enhance the flexibility and diversity of opponent strategies, and FS represents a fuzzy logic-based method for switching between opponent strategy libraries, periodically selecting the strategy library for the next training phase based on training trends and model performance. Finally, the effectiveness of the proposed algorithm is validated through comparisons with the landmark methods in aerial combat, namely, the genetic fuzzy tree (GFT) algorithm and the expert-designed weapon engagement zones (WEZs) algorithm, demonstrating a significant improvement in rewards and achieving a win rate of at least 82.3%.

Pre-Assignment Problem for Unique Minimum Vertex Cover on Bounded Clique-Width Graphs

Horiyama et al. (AAAI 2024) considered the problem of generating instances with a unique minimum vertex cover under certain conditions. The Pre-assignment for Uniquification of Minimum Vertex Cover problem (shortly PAU-VC) is the problem, for given a graph G, to find a minimum set S of vertices in G such that there is a unique minimum vertex cover of G containing S. We show that PAU-VC is fixed parameter tractable parameterized by clique-width, which improves an exponential algorithm for trees given by Horiyama et al. Among natural graph classes with unbounded clique-width, we show that the problem can be solved in polynomial time on split graphs and unit interval graphs.

The role of hypoxia-senescence co-related molecular subtypes and prognostic characteristics in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is known for its high invasiveness, high fatality rate. Both hypoxia and senescence play crucial roles in the initiation and progression of cancer, yet their prognostic implications in HCC are yet to be fully understood. The hypoxia-senescence co-related genes (HSCRGs) were screened from public databases. Transcriptome data and clinical information were obtained from patients with HCC using the Cancer Genome Atlas, GSE76427, and International Cancer Genome Consortium (ICGC). The random forest tree algorithm was used to identify the characteristic genes of the disease, and the genes were verified by related experiments. SVM algorithm was used to classify HCC patients based on HSCRGs. The prediction model based on HSCRGs was established by LASSO, univariate and multivariate COX regression analysis. We used the ICGC for outside validation. The risk score model was analyzed from subgroup analysis, immune infiltration, and functional strength. The expression patterns of key prognostic genes in tumor microenvironment were decoded by single cell analysis. A total of 184 HSCRGs were identified. The expression pattern and functional characteristics of MLH1 gene in HCC were verified. Two HCC subtypes were identified based on HSCRGs. Then, a prediction model based on HSCRGs was established, and risk score was identified as an independent prognostic indicator of HCC. A new nomogram is constructed and shows good prediction ability. We further determined that the level of infiltration of immune cells and the expression of immune checkpoints are significantly affected by the risk score. The immune microenvironment was different between the two risk groups. The high-risk group was dominated by immunosuppressed cells, and the prognosis was poor. Single-cell analysis revealed the expression of seven key prognostic genes in the tumor microenvironment. Finally, qPCR results further verified the expression levels of seven prognostic genes. HSCRGs are of great significance in the prognosis prediction, risk stratification and targeted therapy of patients with HCC.

Prediction of cardiovascular disease based on multiple feature selection and improved PSO-XGBoost model

Cardiovascular disease is a common disease that threatens human health. In order to predict it more accurately, this paper proposes a cardiovascular disease prediction model that combines multiple feature selection, improved particle swarm optimization algorithm, and extreme gradient boosting tree. Firstly, the dataset is preprocessed, and an XGBoost cardiovascular disease prediction model is constructed for model training and compare it with other algorithms. Then, combined with two factor Pearson correlation analysis and feature importance ranking, multiple feature selection is performed, with the optimal feature subset as the feature input. Finally, the improved particle swarm optimization algorithm is used to adjust the hyperparameters of the extreme gradient boosting tree algorithm, and selecting the optimal hyperparameter combination to construct the MFS-DLPSO-XGBoost model. The recall, precision, accuracy, F1 score, and area under the ROC curve (AUC) of the MFS-DLPSO-XGBoost model reached 71.4%, 76.3%, 74.7%, 73.6%, and 80.8%, respectively, which increased by 3.6%, 3.2%, 2.7%, 3.2%, and 2.3% compared to XGBoost. The results indicate that the model proposed in this article has good classification performance and can provide assistance for doctors and patients in predicting and preventing heart disease.

Extracting PAC Decision Trees from Black Box Binary Classifiers: The Gender Bias Study Case on BERT-based Language Models

Decision trees are a popular machine learning method, valued for their inherent explainability. In Explainable AI, decision trees serve as surrogate models for complex black box AI models or as approximations of parts of such models. A key challenge of this approach is assessing how accurately the extracted decision tree represents the original model and determining the extent to which it can be trusted as an approximation of its behaviour. In this work, we investigate the use of the Probably Approximately Correct (PAC) framework to provide a theoretical guarantee of fidelity for decision trees extracted from AI models. Leveraging the theoretical foundations of the PAC framework, we adapt a decision tree algorithm to ensure a PAC guarantee under specific conditions. We focus on binary classification and conduct experiments where we extract decision trees from BERT-based language models with PAC guarantees. Our results indicate occupational gender bias in these models, which confirm previous results in the literature. Additionally, the decision tree format enhances the visualization of which occupations are most impacted by social bias.

Assessing safety in horizontal curves using surrogate safety measures and machine learning

Horizontal curves (HCs) are one of the most safety–critical elements of the road. Crashes are rare events and working with them is challenging. Surrogate safety measures (SSM) can be suitable substitutes for them. In this paper, with the help of a decision tree algorithm and SSMs; the impact of different variables is assessed on the safety of HCs. A variety of variables relevant to drivers’ characteristics, HC specifications, and the environment are considered in order to assess the role they play in HC safety. SSMs and machine learning have not been used to assess the safety of HCs comprehensively. The method is applied for a case study on the rural roads in Iran. Results indicate that the curve radius and speed in the tangent section before the HC have the most significant impact on its safety. The critical threshold for these variables were determined as 358 m and 23 m/s, respectively. The most critical characteristics of a driver when it comes to safely handling HCs are their driving experience, their crash history and education level. The environmental condition did not have a significant impact on HC’s safety.

Dynamic topology adaptability of adaptive multimodal transmission strategy based on environment perception in multi-hop routing of 5G vehicle network

In multi-hop routing of 5G vehicle network, node movement and link failure often lead to frequent changes in network topology, which in turn cause delay and packet loss problems. A multimodal transmission strategy based on environment perception is proposed in this study to achieve adaptive switching of routing protocols. Vehicle-mounted sensors are used to collect location, speed, network load and traffic density information in real-time. Then, graph sample and aggregation (GraphSAGE) is used to process the network topology and extract node and edge features of the data. The features are input into gated recurrent unit (GRU) for time series modeling to predict the link node movement pattern. Then, ad hoc on-demand distance vector routing (AODV), greedy perimeter stateless routing (GPSR) and dynamic source routing (DSR) are integrated, and the best protocol is automatically selected through the classification and regression trees (CART) algorithm. Finally, a route request packet (RREQ) is generated and broadcast according to the selected routing protocol. After being processed by the intermediate node, the route reply packet (RREP) is returned to the source node to achieve real-time update of the routing table and maintain the link status. The results show that when the number of nodes reaches 1200, the system delay is 146.99 ms; when the average vehicle speed is 30 km/h and the network load is 50 Mbps, the packet loss rate of switching to the DSR protocol is only 0.833%. The method can significantly reduce the real-time delay in multi-hop routing of 5G vehicle network.Clinical trial number: Not applicable.

Instability of Financial Time Series Revealed by Irreversibility Analysis

Since the 2008 global economic crisis, the detection of financial instabilities has garnered extensive research attention, particularly through the application of time-series analysis. In this study, a novel time-series analysis method, integrating the Kullback–Leibler Divergence (KLD) metric with a sliding window technique, is proposed to detect instabilities in time-series data, especially in financial markets. Global financial time series from 2004 to 2022 were analyzed. The raw time series were preprocessed into return rate series and transformed into complex networks using the directed horizontal visibility graph (DHVG) algorithm, effectively preserving temporal variabilities in network topologies. The KLD method was evaluated through both retrospective analysis and real-time monitoring. It successfully identified idiosyncratic incidents in the financial market, correlating them with specific economic events. Compared to traditional metrics (e.g., moments) and econometric methods, KLD demonstrated superior performance in capturing sequence information and detecting anomalies without requiring linear regression models. Although initially designed for financial data, the KLD method is versatile and can be applied to other types of time series as well.

DTreePred: an online viewer based on machine learning for pathogenicity prediction of genomic variants

BackgroundA significant challenge in precision medicine is confidently identifying mutations detected in sequencing processes that play roles in disease treatment or diagnosis. Furthermore, the lack of representativeness of single nucleotide variants in public databases and low sequencing rates in underrepresented populations pose defies, with many pathogenic mutations still awaiting discovery. Mutational pathogenicity predictors have gained relevance as supportive tools in medical decision-making. However, significant disagreement among different tools regarding pathogenicity identification is rooted, necessitating manual verification to confirm mutation effects accurately.ResultsThis article presents a cross-platform mobile application, DTreePred, an online visualization tool for assessing the pathogenicity of nucleotide variants. DTreePred utilizes a machine learning-based pathogenicity model, including a decision tree algorithm and 15 machine learning classifiers alongside classical predictors. Connecting public databases with diverse prediction algorithms streamlines variant analysis, whereas the decision tree algorithm enhances the accuracy and reliability of variant pathogenicity data. This integration of information from various sources and prediction techniques aims to serve as a functional guide for decision-making in clinical practice. In addition, we tested DTreePred in a case study involving a cohort from Rio Grande do Norte, Brazil. By categorizing nucleotide variants from the list of oncogenes and suppressor genes classified in ClinVar as inexact data, DTreePred successfully revealed the pathogenicity of more than 95% of the nucleotide variants. Furthermore, an integrity test with 200 known mutations yielded an accuracy of 97%, surpassing rates expected from previous models.ConclusionsDTreePred offers a robust solution for reducing uncertainty in clinical decision-making regarding pathogenic variants. Improving the accuracy of pathogenicity assessments has the potential to significantly increase the precision of medical diagnoses and treatments, particularly for underrepresented populations.

FARMING RECOMMENDATION SYSTEM USING KNN ALGORITHM

This study proposes a Crop Recommendation System (CRS) using Decision Tree algorithm to provide personalized crop recommendations to farmers. The system utilizes a dataset of soil parameters, climate conditions, and crop characteristics to predict the most suitable crop for a given farm. The Decision Tree algorithm is employed to classify crops based on their suitability for specific soil and climate conditions. The system aims to improve crop yields, reduce resource waste, and promote sustainable agriculture practices. By leveraging machine learning and data analytics, the CRS provides actionable insights to farmers, enabling them to make informed decisions about crop selection. The proposed system has the potential to transform agriculture practices, ensuring food security and sustainability. The results of this study demonstrate the effectiveness of the Decision Tree algorithm in predicting suitable crops, with an accuracy of 90%. Keywords: - Agriculture - Crop Recommendation - Decision Tree Algorithm - Machine Learning - Data Analytics - Precision Farming

Shale wastewater treatment policies recommended by integrated knowledge graph and probability-based algorithms.

Shale wastewater (SWW) has received much attention recently due to its non-ignorable threat to the environment and human health. Selection of an appropriate SWW treatment technology or a set of technology combinations could be a challenge particularly when no substantial professional-knowledge (or prior experience) is available. This paper develops a modeling framework integrating knowledge graph (KG) and probability-based recommendation algorithms to produce SWW treatment policies without depending on conventional physically based mathematical models and their associated quantitative data. The model is applied to the shale regions in China, including Chongqing city, the provinces of Sichuan, Yunnan, Guizhou, Shaanxi, and Inner Mongolia Autonomous Region, and utilizes the Monte-Carlo (MC) technique to assess the stability of the output policies. Results show that chemical precipitation, ultrafiltration, membrane bioreactor, and electrodialysis in Knowledge Graph Convolutional Networks (KGCN), as well as ultrafiltration, electrocoagulation, reverse osmosis, and electrocatalytic oxidation in RippleNet, are all preferentially recommended in one scenario, with the MC-based probabilities all higher than 0.86, indicating the stability of recommendation results and robustness of the model. Future studies would focus on improving the current KG and algorithms and offering explanatory mechanisms behind policy recommendations.