Decision-making Model Research Articles

Influence of citizen relationship management system on citizen participation in Taiwan: A participatory politics perspective

Although studies have investigated the development of citizen relationship management (CRM) systems in various cities, no understanding exists regarding how CRM systems operate and how they influence citizen participation. Moreover, limited studies have been conducted regarding the political factors that influence citizen participation through CRM systems. Drawing from data obtained through interviews with key stakeholders involved in the implementation of a CRM system in Taiwan, the present study comprehensively analyzed the primary political characteristics and effects of this system, outlined the political factors influencing system use, and formulated suggestions for mitigating the influence of politics on the system. The findings reveal that the development of the citizen relationship management system was constrained by potential political factors in public policy development. These factors included the dynamics of power relations between citizens and local governments, the politicization of policy processes, conflicts in policy decision-making models involving top-down and bottom-up approaches, the political intentions and motives of stakeholders, and the influence of potential policy actors. Considering the case of the Taiwanese citizen relationship management system, this study provides suggestions and guidance for policymakers aiming to minimize political influence on citizen participation, with a focus on tailoring these approaches to meet the specific public service needs of citizens.

Deep learning for detecting prenatal alcohol exposure in pediatric brain MRI: a transfer learning approach with explainability insights.

Prenatal alcohol exposure (PAE) refers to the exposure of the developing fetus due to alcohol consumption during pregnancy and can have life-long consequences for learning, behavior, and health. Understanding the impact of PAE on the developing brain manifests challenges due to its complex structural and functional attributes, which can be addressed by leveraging machine learning (ML) and deep learning (DL) approaches. While most ML and DL models have been tailored for adult-centric problems, this work focuses on applying DL to detect PAE in the pediatric population. This study integrates the pre-trained simple fully convolutional network (SFCN) as a transfer learning approach for extracting features and a newly trained classifier to distinguish between unexposed and PAE participants based on T1-weighted structural brain magnetic resonance (MR) scans of individuals aged 2-8 years. Among several varying dataset sizes and augmentation strategy during training, the classifier secured the highest sensitivity of 88.47% with 85.04% average accuracy on testing data when considering a balanced dataset with augmentation for both classes. Moreover, we also preliminarily performed explainability analysis using the Grad-CAM method, highlighting various brain regions such as corpus callosum, cerebellum, pons, and white matter as the most important features in the model's decision-making process. Despite the challenges of constructing DL models for pediatric populations due to the brain's rapid development, motion artifacts, and insufficient data, this work highlights the potential of transfer learning in situations where data is limited. Furthermore, this study underscores the importance of preserving a balanced dataset for fair classification and clarifying the rationale behind the model's prediction using explainability analysis.

Risk factors for the development of refeeding syndrome in adults: A systematic review.

Identifying patients with a particularly high risk of refeeding syndrome (RFS) is essential for taking preventive measures. To guide the development of clinical decision-making and risk prediction models or other screening tools for RFS, increased knowledge of risk factors is needed. Therefore, we conducted a systematic review to identify risk factors for the development of RFS. PubMed, EMBASE, Cochrane Library, and Web of Science were searched from January 1990 until March 2023. Studies investigating demographic, clinical, drug use, laboratory, and/or nutrition factors for RFS were considered. The Newcastle-Ottawa Scale was used to appraise the methodological quality of included studies. Of 1589 identified records, 30 studies were included. Thirty-three factors associated with increased risk of RFS after multivariable adjustments were identified. The following factors were reported by two or more studies, with 0-1 study reporting null findings: a previous history of alcohol misuse, cancer, comorbid hypertension, high Acute Physiology and Chronic Health Evaluation II score, high Sequential Organ Failure Assessment score, low Glasgow coma scale score, the use of diuretics before refeeding, low baseline serum prealbumin level, high baseline level of creatinine, and enteral nutrition. The majority of the studies (20, 66.7%) were of high methodological quality. In conclusion, this systematic review informs on several risk factors for RFS in patients. To improve risk stratification and guide development of risk prediction models or other screening tools, further confirmation is needed because there were a small number of studies and a low number of high-quality studies on each factor.

Strategy for striking the omnichannel balance in Retail 4.0

PurposeThe rise of Industry 4.0 led to digitally-enabled evolutionary and radical changes in all branches of the retail industry, resulting in the emergence of the distinct term “Retail 4.0”. Within this paradigm, particular emphasis is placed on forming a balanced system of omnichannel sales and customer service, allowing reaching a synergistic effect in the face of constant changes, turbulence and uncertainty in the business environment. The main objective of this study is to offer and justify a practical strategy for optimal utilization of sales channels and customer service provision within the Retail 4.0 paradigm.Design/methodology/approachThe conceptual argument of the study is based on the review of the literature and illustrative case studiesFindingsThe decision-making model proposed in this study provides a roadmap for retailers. It underscores the need for a data-driven approach, where decisions are informed by real-time analytics and customer insights. This model also advocates for a flexible yet structured approach to managing various sales channels, ensuring that each channel complements and enhances the other.Originality/valueThe study offers and justifies an original five-stage process model for forming a balanced system of omnichannel sales and customer service.

Determination of Single Sampling Attribute Plans Based Upon Dodge Roaming Model with Application

Bayesian sampling plans for production inspection involve using a sampling method to assess the features of the plan, under the assumption that defect rates fluctuate randomly among different production batches. This results in a likelihood distribution that can be established through experience and the quality information at hand. In this study, the parameters of a single Bayesian sampling plan were determined using the Beta-Binomial distribution, and were subsequently contrasted with parameters from other single sampling plans. Based on research findings, (Ala corporation for soft drinks) oversees the control of product quality. Since the variable fluctuates randomly between manufacturing batches, 120 batches were selected to calculate the defect rate by analyzing batch size and number of defective items. Applying Bayesian and decision-making models can lead to the development of a single sampling inspection procedure that closely approximates the actual quality level. When the decision-making model was used, the researchers discovered that the sample size was smaller and led to lower inspection costs compared to other inspection plans.

Formation Cooperative Intelligent Tactical Decision Making Based on Bayesian Network Model

This paper proposes a method based on a Bayesian network model to study the intelligent tactical decision making of formation coordination. For the problem of formation coordinated attack target allocation, a coordinated attack target allocation model based on the dominance matrix is constructed, and a threat degree assessment model is constructed by calculating the minimum interception time. For the problem of real-time updating of the battlefield situation in the formation confrontation simulation, real-time communication between the UAV formation on the battlefield is realized, improving the efficiency of communication and target allocation between formations on the battlefield. For the problem of UAV autonomous air combat decision making, on the basis of the analysis of the advantage function calculation of the air combat decision-making model and a Bayesian network model analysis, the network model's nodes and states are determined, and the air combat decision-making model is constructed based on the Bayesian network. Our formation adopts the Bayesian algorithm strategy to fight against the blue side's UAVs, and the formation defeats the blue UAVs through coordinated attack, which proves the reasonableness of coordinated target allocation. An evaluation function is established, and the comprehensive scores of our formation are compared with those of other algorithms, which proves the accuracy and intelligibility of the decision making of the Bayesian network.

Evaluation and benchmarking of research-based microgrid systems using FWZIC-VIKOR approach for sustainable energy management

Microgrid (MG) is one of the technologies considered in the direction of providing green and sustainable energy resources for local communities. Ensuring the best performance of these MG technologies requires extensive research to provide the most efficient system. Research-based microgrids (RB-MGs) play a vital role in the development of green energy platforms, as microgrid applications vary according to different scenarios and locations. Selecting the best research-based microgrid ensures providing local communities and stakeholders with well-tested and examined MG systems. Assessing research-based microgrid systems (RB-MG) for sustainable green applications poses a challenging multi-attribute decision-making (MADM) problem. These complexities encompass the consideration of several evaluation criteria, the relative importance of these criteria, variations in data, and the inherent trade-offs and conflicts between these factors. Crisp and definite values to evaluate the research-based microgrids could not be found despite a comprehensive investigation. In this regard, appraisals and opinions of experts and professionals in providing sustainable energy with vast knowledge and experience in assessment, selection, installation, and operation were addressed as data. A novel decision-making model was developed to evaluate and select the most proper RB-MG system by processing these data. This study proposes an integrated MADM modelling approach using Fuzzy Weighted with Zero Inconsistency (FWZIC) method in conjunction with the Vlse-kriterijumska Optimizcija I Kaompromisno Resenje (VIKOR) method. The underlying process starts with constructing a decision matrix (evaluation criteria intersectioned with RB-MGs). Then, evaluation criteria are weighted using FWZIC, and the RB-MGs are ranked for each category using VIKOR. The results derived from FWZIC weights provide valuable insights. Key criteria such as 'installed power (KW)' and 'storage capacity (C3)' show notable values of 0.159 and 0.151, respectively, underscoring their importance in identifying optimal RB-MGs. These weights and alternatives were used to rank the highest RB-MG, which is LIER-CIRCE of the average PV power group, and Ormazabal from the 'Highest PV Power' group. Ormazabal obtained the lowest Qi (0.426). For the average PV power group, alternative number 7 (Atenea Centre) ranked as the best alternative with the lowest Qi among other RB-MGs in the same group (0.158107). Comparative assessments with various MCDM methods reveal strong correlations with TOPSIS and MABAC, but negative correlations with MAIRA. Additionally, there is a statistical difference in grouping by PV installed power (KW) or MPC.

A predictive machine-learning model for clinical decision-making in washed microbiota transplantation on ulcerative colitis

Background and AimMachine learning based on clinical data and treatment protocols for better clinical decision-making is a current research hotspot. This study aimed to build a machine learning model on washed microbiota transplantation (WMT) for ulcerative colitis (UC), providing patients and clinicians with a new evaluation system to optimize clinical decision-making.MethodsPatients with UC who underwent WMT via mid-gut or colonic delivery route at an affiliated hospital of Nanjing Medical University from April 2013 to June 2022 were recruited. Model ensembles based on the clinical indicators were constructed by machine-learning to predict the clinical response of WMT after one month.ResultsA total of 366 patients were enrolled in this study, with 210 patients allocated for training and internal validation, and 156 patients for external validation. The low level of indirect bilirubin, activated antithrombin III, defecation frequency and cholinesterase and the elderly and high level of creatine kinase, HCO3- and thrombin time were related to the clinical response of WMT at one month. Besides, the voting ensembles exhibited an area under curve (AUC) of 0.769 ± 0.019 [accuracy, 0.754; F1-score, 0.845] in the internal validation; the AUC of the external validation was 0.614 ± 0.017 [accuracy, 0.801; F1-score, 0.887]. Additionally, the model was available at https://wmtpredict.streamlit.app.ConclusionsThis study pioneered the development of a machine learning model to predict the one-month clinical response of WMT on UC. The findings demonstrate the potential value of machine learning applications in the field of WMT, opening new avenues for personalized treatment strategies in gastrointestinal disorders.Trial registrationclinical trials, NCT01790061. Registered 09 February 2013 - Retrospectively registered, https://clinicaltrials.gov/study/NCT01790061

Development and implementation of digital pedagogical support systems in the context of educational equity

In response to the covid-19 pandemic, the digital strategy of education has become a key pedagogical approach for higher engineering disciplines. In this complex environment, the outcome-oriented higher engineering discipline faces the challenge of educational equity in terms of curriculum design and learning outcome assessment for its online engineering practical courses. In order to solve this problem, this study develops a digital teaching assistant system to facilitate the reform of educational equity in higher engineering disciplines. The teaching and learning functions of the system aim to support the interaction between teachers and students in the teaching process and the visual display of learning outcomes, and its intelligent evaluation and analysis function is based on the multi-criterion group decision-making model of Quality Function Deployment (QFD) combined with t-test to realize the evaluation of course learning outcomes. The results show that the academic performance of this system is significantly better than that of other similar systems. The statistical results of the teacher-student satisfaction survey of the two systems show that the teacher-student interaction and multi-dimensional learning evaluation analysis report function provided by the system are the most highly recognized, and the system also has better educational equity in resource recommendation, interaction and collaboration, learning achievement display and learning achievement evaluation, etc. In addition, the system is more in line with the teaching characteristics of higher engineering disciplines, which can provide effective assistance for teachers of higher engineering disciplines to improve teaching plan and cultivate students’ disciplinary practicality, consequently creating favorable conditions for the establishment of teaching equity.

Optimal Feature Picking for Intrusion Detection on The Basis of Explainable Artificial Intelligence

Traditional security mechanisms for intrusion detection are strong, and the use of machine learning algorithms to detect intrusion into IoT networks has increased. As a result, the efficiency of the IoT network has increased and an effective model can be developed to detect attacks on the network. UNSW-NB15 is an IoT-based publicly available dataset for traffic data that contains general activity and malicious activity. Using this dataset, the key features were selected and these features fed different classifiers for training and classifying the attack in the network. Ann model performance levels of accuracy, the ML classifier, and accompanying algorithms for constructing a digital security system based on packet flow in-network, and features that really can monitor anomalous botnet behaviors proven to be highly efficient. The decision-making model for the classification was visualized using proven Explainable AI (XAI) approaches utilizing Scikit-Learn, LIME, ELI5, and SHAP libraries to boost explainability in classification predictions. The findings showed that XAI is realistic and profitable since security expertise and specialists stand to benefit greatly from combining conventional machine learning methods with Explainable AI (XAI) methodologies.

Multi-index evaluation on reinforcement programs for frame structures based on life cycle theory and time-varying reliability

Under the mandates of economic and environmental sustainability, the consideration of reinforcement engineering must extend beyond mere enhancement effects and short-term project costs. As a long-term engineering activity, reinforcement significantly impacts urban economies and environments. Although extensive research has evaluated the costs or environmental impacts of reinforcement engineering based on the whole life cycle theory, existing studies often focus on single indicators without adequately integrating them with other domains. Using a reinforced concrete frame structure as a case study, this paper develops a combined evaluation decision-making model integrating the Analytic Hierarchy Process for subjective assessment and an enhanced Rough Set method for objective evaluation. This model comprehensively assesses the seismic performance, economic costs, and environmental impacts of various reinforcement strategies. The results indicate that the combined strategy of enlarging column sections and carbon fiber reinforced polymer strengthening beams performs best in seismic performance, long-term economic benefits, and environmental impacts. Grounded in practical projects, this study adjusts the whole life cycle cost model to better align with engineering maintenance realities and introduces Rough Set theory to address deficiencies in objective indicator weighting. This research offers insights and guidance for leveraging information technology in resolving multi-criteria evaluation decision-making challenges in reinforcement engineering solutions.

Exploring adolescent-facing US clinicians' perceptions of their contraceptive counseling and use of shared decision-making: A qualitative study.

Adolescent contraceptive decision-making is influenced by a number of patient and clinician-driven factors. Although the AAP continues to endorse an efficacy-based model of contraceptive counseling, many professional organizations are shifting to a shared decision-making model as the optimal approach for providing unbiased and patient-driven contraceptive counseling. While SDM is intended to reduce the influence of clinician bias, it can exacerbate inequity if a clinician tailors a conversation based on their assumptions of a patient's goals or preferences. In this qualitative study, we explored self-reported contraceptive counseling practices among US-based clinicians who see adolescent patients to assess how these practices create barriers or facilitators to SDM and person-centered contraceptive care. We interviewed 16 clinicians at the 2022 AAP Annual Meeting who counsel adolescent patients about contraception. We used thematic content analysis to analyze interview transcripts using Dedoose. We identified six aspects of contraceptive counseling that clinicians commonly employed with adolescent patients. These were: (1) sociodemographic characteristics driving counseling, (2) reliance on tiered effectiveness counseling, (3) initiating counseling conversations using "ask then explain" or "explain then ask" approaches, (4) emphasis on teen pregnancy prevention, (5) the influence of method accessibility on counseling, and (6) parental involvement in decision-making and patient confidentiality. We describe how these themes align with or diverge from each component of the SDM framework. Clinicians in this study frequently engaged in non-patient-centered techniques during contraceptive counseling with adolescents. These findings can inform practice recommendations to support clinicians in providing high-quality contraceptive counseling using shared decision-making.

Explainable Machine Learning Approach to Prediction of Prolonged Intesive Care Unit Stay in Adult Spinal Deformity Patients: Machine Learning Outperforms Logistic Regression.

Retrospective cohort study. Prolonged ICU stay is a driver of higher costs and inferior outcomes in Adult Spinal Deformity (ASD) patients. Machine learning (ML) models have recently been seen as a viable method of predicting pre-operative risk but are often 'black boxes' that do not fully explain the decision-making process. This study aims to demonstrate ML can achieve similar or greater predictive power as traditional statistical methods and follows traditional clinical decision-making processes. Five ML models (Decision Tree, Random Forest, Support Vector Classifier, GradBoost, and a CNN) were trained on data collected from a large urban academic center to predict whether prolonged ICU stay would be required post-operatively. 535 patients who underwent posterior fusion or combined fusion for treatment of ASD were included in each model with a 70-20-10 train-test-validation split. Further analysis was performed using Shapley Additive Explanation (SHAP) values to provide insight into each model's decision-making process. The model's Area Under the Receiver Operating Curve (AUROC) ranged from 0.67 to 0.83. The Random Forest model achieved the highest score. The model considered length of surgery, complications, and estimated blood loss to be the greatest predictors of prolonged ICU stay based on SHAP values. We developed a ML model that was able to predict whether prolonged ICU stay was required in ASD patients. Further SHAP analysis demonstrated our model aligned with traditional clinical thinking. Thus, ML models have strong potential to assist with risk stratification and more effective and cost-efficient care.

Collaborative task decision-making of multi-UUV in dynamic environments based on deep reinforcement learning

ABSTRACT The problem of collaborative task decision-making for unmanned underwater vehicles (UUVs) in an unknown dynamic ocean environment is investigated. In view of the unknown marine environment, a partially observable Markov decision process is designed to achieve partially observable path planning for multi-UUV. Aiming at the problems of long planning time, large amount of data, and insufficient multi-task decision-making capability in the process of multi-UUV underwater collaborative operation, a multi-UUV collaborative task decision-making model based on the multi-agent twin delayed deep deterministic policy gradient (MATD3) algorithm for the dynamic environment is constructed. The implementation of the centralised training with distributed execution (CT-DE) training framework enables each UUV to possess autonomous decision-making capability and ensures task safety under weak communication conditions. The pre-training phase shows that the MATD3 algorithm outperforms the multi-agent deep deterministic policy gradient (MADDPG) algorithm for training multi-UUV autonomous decision-making scenarios in dynamic environments. The simulation experiment results verify that the autonomous decision-making method based on the MATD3 algorithm can effectively solve the multi-UUV collaborative task decision-making problem in unknown dynamic environments, and the task process satisfies the requirements of real-time, safety and economy.

Analyzing the causal dynamics of circular-economy drivers in SMES using interpretive structural modeling

The circular economy has emerged as a crucial way for companies to achieve their sustainability goals. Numerous businesses, especially small and medium-sized enterprises (SMEs), are integrating circular-economy projects into their operations. However, this undertaking presents multiple challenges as many managers must grapple with constraints in resources and expertise. This study’s primary objective is to develop a process-oriented decision-making system designed to deal with complex circular-economy scenarios. The proposed analysis system can help SMEs identify the driving forces behind circular-economy principles and evaluate the intricate connections between these determinants, using a unique combination of multiple criteria decision analysis methods (i.e., cognitive mapping, and interpretive structural modeling). Collaborative sessions involving circular-economy experts were instrumental in refining the analysis system, and in-depth discussions with other specialists from the International Labor Organization further enriched this decision-support system. The findings include that circular-economy drivers can be grouped into five clusters: products, processes, policies/regulations, attitudes/behaviors, and communication/awareness. This structured breakdown provides SMEs with the tools to comprehend and address the pivotal factors that shape circular-economy initiatives. This pioneering study thus produced a comprehensive decision-making model attuned to the intricacies of the circular economy while highlighting the benefits of collaborative endeavors involving industry experts and global decision makers.

Multi-Agent Decision-Making in Construction Engineering and Management: A Systematic Review

Construction engineering and management (CEM) involves multiple stakeholders, complex interest relationships, and conflicts. All stakeholders must comprehensively consider the interests relating to a project to make decisions. Appropriate multi-agent decision-making can effectively coordinate and integrate the needs or expectations of all stakeholders, which can reduce conflicts, improve the success probability of the project, maximize the overall returns on interest, and contribute to the project’s sustainability. Existing studies have begun to explore the associated theoretical framework and practical methods for multi-agent decision-making. However, early studies mainly focused on the conceptual theories of decision-making models and processes, such as stakeholder analysis, decision evaluation, and risk management. In recent years, increasing research has concerned the application of multi-agent decision-making in CEM. This paper is the first to use a comprehensive review approach to analyze multi-agent decision-making in CEM, providing an overall perspective. In this paper, 105 journal papers are identified and classified into four categories: (1) main concerns regarding multi-agent decision-making in CEM; (2) tools and methods of multi-agent decision-making in practice; (3) research tools and methods of multi-agent decision-making in CEM; (4) critical points on how to solve multi-agent decision-making problems. The findings of this study offer references for future trends in four regards, namely (1) knowledge management, (2) decision resilience, (3) the fusion of many techniques, and (4) technologies for future research.

Exploring and Improving the Potential Factors of Preschool Teacher Resignation Using the Stratified Bayesian Best-Worst Method

The high turnover rate of preschool teachers in the educational sector threatens the ability to retain competent teaching staff and affects the quality of teaching and the development of early education in many countries. These ramifications are especially poignant given their alignment with the United Nations’ sustainable development goals (SDGs) - notably “quality education,” “good health and well-being,” and “decent work and economic growth.” Reducing the turnover rate of educators, especially at the preschool level, has become an urgent issue for the education community. Therefore, this paper develops a multiple criteria decision-making (MCDM) model based on expert knowledge to construct an evaluation model of the main factors for the resignation of preschool teachers. These factors comprise three main dimensions: personal factors, internal organizational culture, and external environment. First, potential resignation factors were identified through a literature survey and interviews with several experts. Then, a stratified Bayesian best-worst method (SB-BWM) was used to evaluate the importance of these potential factors. The method generated the optimal group weights of the resignation factors and ranked them. The results of this study reveal that the top five resignation factors are high work stress, work-induced emotional exhaustion/job burnout, poor work atmosphere, high workload, and low collaborative relationships with partners. The results can help preschool education operators and education ministries responsible for decision-making to understand the factors leading to the resignation of preschool teachers so that they can develop strategies to improve retention. Management implications are given to improve operational performance and effectively reduce the teacher turnover rate to promote stability in the learning environment so important to early childhood development, which will lead to quality preschool education development.

Promoting the sustainable development of CCUS projects: A multi-source data-driven location decision optimization framework

Carbon Capture, Utilization, and Storage (CCUS) technology is vital for achieving global carbon reduction targets. However, the uncertainties in technology and economic viability are influenced by location. To promote the sustainable development of CCUS technology, the study proposes a data-driven framework for optimizing location decisions. Firstly, the framework considers multiple factors, including geospatial data on resources, risks, power production, transportation, and environment. It also evaluates qualitative and quantitative data across economic, social, environmental, and technological dimensions. Secondly, the two-stage model is conducted as follows: Using Geographic Information System (GIS) technology, the first stage identifies suitable regions for CCUS projects, while the second stage prioritizes these regions using the TODIM method. Further, validated in China, the Junggar Basin, Tarim Basin, Ordos Basin, Sichuan Basin, and Bohai Rim Basin are identified as suitable for CCUS deployment. The Huaneng Luohuang Power Plant is the most conducive location for CCUS projects as pilot demonstrations. Final sensitivity analysis, scenario analysis, and comparative analysis have respectively affirmed the stability, dynamism, and reliability of the model. These analyses have also been instrumental in elucidating the final preferred outcomes under various decision-making preferences and strategic orientations. The framework for decision-making and data-driven priority model for CCUS projects layout proposed in the study can provide technical support and practical evidence for decision-makers in planning CCUS projects and formulating supportive policies.

Correction to: A Large-Scale Group Decision-Making Model Considering Expert Authority Degree and Relationship Evolution Under Social Network

Correction to: A Large-Scale Group Decision-Making Model Considering Expert Authority Degree and Relationship Evolution Under Social Network

Variance Feedback Drift Detection Method for Evolving Data Streams Mining

Learning from changing data streams is one of the important tasks of data mining. The phenomenon of the underlying distribution of data streams changing over time is called concept drift. In classification decision-making, the occurrence of concept drift will greatly affect the classification efficiency of the original classifier, that is, the old decision-making model is not suitable for the new data environment. Therefore, dealing with concept drift from changing data streams is crucial to guarantee classifier performance. Currently, most concept drift detection methods apply the same detection strategy to different data streams, with little attention to the uniqueness of each data stream. This limits the adaptability of drift detectors to different environments. In our research, we designed a unique solution to address this issue. First, we proposed a variance estimation strategy and a variance feedback strategy to characterize the data stream’s characteristics through variance. Based on this variance, we developed personalized drift detection schemes for different data streams, thereby enhancing the adaptability of drift detection in various environments. We conducted experiments on data streams with various types of drifts. The experimental results show that our algorithm achieves the best average ranking for accuracy on the synthetic dataset, with an overall ranking 1.12 to 1.5 higher than the next-best algorithm. In comparison with algorithms using the same tests, our method improves the ranking by 3 to 3.5 for the Hoeffding test and by 1.12 to 2.25 for the McDiarmid test. In addition, they achieve a good balance between detection delay and false positive rates. Finally, our algorithm ranks higher than existing drift detection methods across the four key metrics of accuracy, CPU time, false positives, and detection delay, meeting our expectations.