K-prototype Clustering Research Articles

Construction Method of Information Security Detection based on Clustering Algorithm

A method for K-prototype clustering, which can process mixed data types, is proposed first. An algorithm for information security evaluation of hybrid clusters based on K-prototypes was constructed. This method makes full use of the excellent global optimization performance of PSO and effectively solves the defect that the K-protection function quickly falls into local optimization. Simulation results show that the proposed method can effectively prevent local extreme values and improve overall performance.

Comprehensive analysis of traumatic rupture of the aorta in road traffic crashes: incorporating epidemiological insights and K-prototype clustering

Objectives The identification of crash characteristics associated with traumatic rupture of the aorta (TRA) can significantly enhance countermeasures against TRA. Conventional epidemiological approaches struggle to adequately handle the substantial variability of traffic crash data. Consequently, this study aims to integrate conventional epidemiological analysis with data-driven cluster analysis to more comprehensively analyze TRA-related crash characteristics. Methods A total of 350 unweighted TRA crashes were extracted from traffic crash databases including comprehensive crash details and injury descriptions. Initially, a selection was made of 11 continuous variables and 9 categorical variables, describing crash characteristics. After correlation analysis and principal component analysis were applied to the dataset, K-prototype clustering was finally conducted using 6retained categorical variables and 6 principal components derived from the continuous variables. Results This study found significant age and gender disparities among TRA victims, with 50% falling within the age range of 25–59 years and an overwhelming majority (62.2%) being males. Side impacts emerged as the primary cause of TRA-related crashes (37.2%), followed by collisions with off-road objects (28.6%) and head-on collisions (24.8%). Cluster analyses revealed 6 distinct clusters within the TRA-related crash dataset. These clusters were characterized by factors such as vehicle model year, curb weight, collision dynamics, and seatbelt usage, providing a deeper understanding of the heterogeneity in TRA incidents and their associated factors. Conclusions Although limitations related to available data sources and factors such as accompanying injuries and vehicle weight warrant further comprehensive investigations in the future, this study contributes valuable insights into TRA analysis to enhance understanding and prevention strategies.

12. A data-driven approach to categorize patients with degenerative cervical myelopathy: a K-prototype clustering analysis of the CSORN DCM database

12. A data-driven approach to categorize patients with degenerative cervical myelopathy: a K-prototype clustering analysis of the CSORN DCM database

Optimizing Surgical Outcomes for Intracranial Epidermoid Tumors: A Retrospective Analysis of Clinical Predictors, Surgical Decisions, and Patient Clustering

IntroductionIntracranial epidermoid tumors (ETs) are rare, benign lesions that present significant challenges in neurosurgical management due to their propensity to encase vital neurovascular structures. ObjectiveTo evaluate the impact of clinical, demographic, and tumor-specific factors on surgical decisions (gross total resection [GTR] vs. subtotal resection [STR]) and outcomes and identify patient clusters with distinct profiles and outcomes post-resection. MethodsWe retrospectively analyzed 72 epidermoid brain tumor patients treated from 1998 to 2022, employing multivariable logistic regression for GTR vs. STR predictors and Kaplan-Meier curves for progression-free survival (PFS). K-prototype clustering classified patients based on clinical data. ResultsThe mean age of our cohort was 39.8±20.1 years. 13.9% of patients had a recurrence, with a median PFS of 108 months (IQR 57-206). Seizures significantly predicted GTR (p<0.05), whereas adherence to critical structures reduced GTR likelihood (p<0.05). Initial surgeries more often achieved GTR, correlating with longer PFS (p<0.0001) and reduced recurrence (p<0.01). History of previous ET surgery was predictive of increased recurrent tumor size (p<0.05) and reduced overall PFS (p<0.05). Clustering analysis revealed three clusters with significant differences in recurrence rates (p<0.0001), long term neurological deficits (p<0.05), PFS greater than 10 years (p<0.0001), and significant differences in median PFS between clusters 1 and 3 (p<0.0001) as well as 2 and three (p<0.01). ConclusionThis study emphasizes the importance of tailored surgical strategies in managing intracranial ETs, advocating for GTR to optimize long-term outcomes where possible. Future prospective studies are essential to further refine treatment approaches, enhancing survival for ET patients.

Machine Learning Approaches for Stroke Risk Prediction: Findings from the Suita Study.

Stroke constitutes a significant public health concern due to its impact on mortality and morbidity. This study investigates the utility of machine learning algorithms in predicting stroke and identifying key risk factors using data from the Suita study, comprising 7389 participants and 53 variables. Initially, unsupervised k-prototype clustering categorized participants into risk clusters, while five supervised models including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosted Machine (LightGBM) were employed to predict stroke outcomes. Stroke incidence disparities among identified risk clusters using the unsupervised k-prototype clustering method are substantial, according to the findings. Supervised learning, particularly RF, was a preferable option because of the higher levels of performance metrics. The Shapley Additive Explanations (SHAP) method identified age, systolic blood pressure, hypertension, estimated glomerular filtration rate, metabolic syndrome, and blood glucose level as key predictors of stroke, aligning with findings from the unsupervised clustering approach in high-risk groups. Additionally, previously unidentified risk factors such as elbow joint thickness, fructosamine, hemoglobin, and calcium level demonstrate potential for stroke prediction. In conclusion, machine learning facilitated accurate stroke risk predictions and highlighted potential biomarkers, offering a data-driven framework for risk assessment and biomarker discovery.

Abstract WP266: Prediction of Stroke Incidence Using Machine Learning: The Suita Study

Background: This population-based study investigated the potential of machine learning algorithms to predict stroke incidence and identify important risk factors. This study aimed to evaluate the accuracy of these algorithms in constructing a stroke prediction model. Methods: Participants from the Suita study were included, and baseline measurements were used to predict stroke outcomes over a 15-year follow-up period. In total, 7,389 participants and 51 variables were investigated, including demographics, medical history, medical imaging, laboratory data, and lifestyle habits. Initially, unsupervised K-prototype clustering was used to group participants based on their stroke risk. Subsequently, five supervised models (logistic regression, random forest, support vector machine, extreme gradient boosting, and light gradient boosted machine) were applied to predict the stroke outcomes. The Shapley Additive Explanations (SHAP) method determined the most critical variables. Results: Unsupervised clustering revealed significant differences in stroke incidence among the three identified risk clusters (9.1%, 6.6%, and 3.2%). These clusters were categorized into high-, medium-, and low-risk groups. Among the supervised models, the random forest algorithm demonstrated the best performance. The top ten most important variables for predicting stroke incidence were identified using the SHAP, with age being the most influential variable. Other significant risk markers included systolic blood pressure, hypertension, estimated glomerular filtration rate, metabolic syndrome, and blood sugar level. Additionally, elbow joint thickness and fructosamine, hemoglobin, and calcium levels were found to be potential predictors of stroke risk. Notably, the variables identified by the SHAP were consistent with those obtained from the unsupervised clustering approach in the high-risk group. Conclusion: Machine learning algorithms provide accurate predictions of stroke incidence and offer valuable insights into subclinical markers without the need for prior assumptions of causality. This study presents a data-driven machine-learning framework for stroke risk prediction and biomarker identification.

Efficient Slice Creation in Network Slicing using K-Prototype Clustering and Context-Aware Slice Selection for Service Provisioning

The advent of 5G technology has ushered in a new era of communication where the customization of network services is crucial to meet diverse user demands. Network slicing has emerged as a pivotal technology to achieve this customization. In this research, we present an innovative approach to optimize network slicing in 5G by employing K-Prototype Clustering for slice creation and Context-Aware Slice Selection for efficient resource allocation. In slice creation, we delve into the innovative application of the K-Prototype clustering algorithm. Recognizing that 5G networks encompass numerical and categorical attributes, the K-Prototype algorithm enables the creation of network slices that cater to diverse service requirements. By harnessing this clustering technique, our proposed method optimizes the creation of network slices, resulting in improved resource utilization and reduced network congestion. Furthermore, we introduce the concept of Context-Aware Slice Selection, which considers the dynamic and evolving nature of network demands. Context-awareness ensures that network slices are selected based on real-time contextual information, enabling a more adaptive and responsive network. This approach leads to the efficient allocation of resources and a higher quality of service for end-users. To evaluate the performance of our proposed methodology, we employ key performance metrics, including slice selection accuracy, slice selection delay, and radio link failure. Through comprehensive testing and analysis, our research demonstrates that our approach consistently outperforms existing methods in terms of these metrics.

Research on the Language Value of College Students’ Ideological and Political Education in the Internet Era

Abstract In the digital landscape, the language of ideological and political education for college students acquires new dimensions and faces unique challenges. Through the analysis of survey data from 1,025 college students, employing the K-prototype clustering algorithm and an enhancement of the Apriori algorithm, this study explores the significant influence of language on students’ emotional and cognitive responses. A striking 90% of participants displayed a strong affinity for media promoting patriotic themes, while over 52% regularly engaged in political discourse, highlighting the language’s potent effect on shaping civic attitudes. Nevertheless, the findings also suggest a pressing need to refine the linguistic approach regarding style and substance to maximize educational outcomes. By examining the contemporary role of language in shaping ideological and political perspectives among students, this paper sheds light on avenues for optimizing educational strategies in the Internet era.

A data-driven approach to categorize patients with degenerative cervical myelopathy: a K-prototype clustering analysis of the CSORN DCM database

A data-driven approach to categorize patients with degenerative cervical myelopathy: a K-prototype clustering analysis of the CSORN DCM database

Outsourced and Privacy-Preserving Collaborative k-Prototype Clustering for Mixed Data via Additive Secret Sharing

Outsourced cloud computing can be considered as an effective way to overcome the data island among users and relieve the pressure of limited resources. However, due to the concerns about trust in cloud servers, outsourcing the users’ data and model training task has considerable privacy disclosure risks. This paper presents a PriKPM scheme by using additive secret sharing (ASS), so as to implement the privacy-preserving k-prototype clustering for mixed data (i.e., including numerical and categorical attributes). In PriKPM, data samples are randomly split into two shares and delivered offline to two collaborative servers. We design a secure initialization method for determining the location and number of cluster centers. Then, both servers securely calculate the mixed distance between samples and cluster centers, and execute the samples partion and cluster updating operations. An efficient and secure comparison protocol is developed to offer flexibly the “less than or equal” and “equal” functions during the entire clustering process. Furthermore, theoretical analysis proves the effectiveness and security of PriKPM. Sufficient experiments demonstrate that PriKPM is computationally more efficient than existing secure clustering works. PriKPM can achieve the approximate accuracy of the plaintext k-prototype clustering scheme.

The interplay between social media use and problematic internet usage: Four behavioral patterns

ObjectiveThe study aims to identify typical interplay between the use of social media apps on smartphones and Problematic Internet Usage (PIU). MethodOur study utilizes data from a smartphone app that objectively monitors user usage, including the apps used and the start and finish times of each app session. This study included 334 participants who declared a need to be aware of their smartphone usage and control it. Problematic Internet Usage (PIU) was measured using the Problematic Internet Use Questionnaire-Short Form-6 (PIUQ-SF6). The total PIU score can range from 6 to 30, with a score above 15 indicating that a person is at risk of PIU. Time spent on Social Media (SM) apps of Facebook, WhatsApp, and Instagram, and whether people used each of these apps were studied along with the total PIU score. K-Prototype clustering was utilized for the analysis. ResultsFour distinct clusters, typifying the relationship between social media use and PIU, were identified. All the individuals in Cluster 1 (Light SM Use Cluster; Cluster size = 270, 80.84% of total dataset) spent between 0 and 109.01 min on Instagram, between 0 and 69.84 min on Facebook, and between 0 and 86.42 min on WhatsApp and its median PIU score was 17. Those who were in cluster 2 (Highly Visual SM Cluster; Cluster size = 23, 6.89% of total dataset) all used Instagram, and each member spent between 110 and 307.63 min on Instagram daily. The cluster median PIU score and average daily usage of Instagram were respectively 20 and 159.66 min. Those who were in Cluster 3 (Conversational SM Cluster; Cluster size = 19, 5.69% of total dataset) all used WhatsApp, and spent between 76.68 and 225.22 min on WhatsApp daily. The cluster median PIU score and average time spent per day on WhatsApp were 20 and 132.65 min, respectively. Those who were in Cluster 4 (Social Networking Cluster; (Cluster size = 22, 6.59% of total dataset) all used Facebook, and each spent between 73.09 and 272.85 min daily on Facebook. The cluster median PIU score and average time spent per day on Facebook were 18 and 133.61 min respectively. ConclusionThe clusters indicate that those who use a particular social media app spend significantly less time on other social media apps. This indicates that problematic attachment to social media occurs primarily for one of three reasons: visual content and reels, conversations with peers, or surfing network content and news. This finding will help tailor interventions to fit each cluster, for example by strengthening interpersonal skills and resistance to peer pressure in the case of Cluster 3 and increasing impulse control in the case of Cluster 2.

An investigation into epidemiological situations of COVID-19 with fuzzy K-means and K-prototype clustering methods

The ten countries with the highest population during the pandemic were analyzed for clustering based on the quantitative numbers of COVID-19 and policy plans. The Fuzzy K-Means (FKM) and K-prototype algorithms were used for clustering, and various performance indices such as Partition Coefficient (PC), Partition Entropy (PE), Xie-Beni (XB), and Silhouette Fuzzy (SIL.F) were used for evaluating the clusters. The analysis included variables such as confirmed cases, tests, vaccines, school and workplace closures, event cancellations, gathering restrictions, transport closures, stay-at-home restrictions, international movement restrictions, testing policies, facial coverings, and vaccination policy statuses. PC, PE, XB, and SIL.F indices were used to analyze the performance indices of the clusters. The Elbow method was used to analyze the performance evaluations for the K-prototype. The K-prototype algorithm's performance evaluations were analyzed using the Elbow method, and the optimum number of clusters for both methods was found to be two. The first cluster included Brazil, Mexico, Nigeria, Bangladesh, US, Indonesia, Russia, and Pakistan, while the second cluster comprised India and China. The analysis also examined the relationship between population and confirmed tests and vaccines, and standardization was made for the country with the largest population for significant correlations. The results showed that the FKM method was superior to the K-prototype method in terms of clustering. In conclusion, it is crucial to accurately evaluate COVID-19 data for countries and develop appropriate policies. The clustering analysis using the FKM and K-prototype algorithms provides valuable insights into identifying groups of countries with similar COVID-19 data and policy plans.

Identification of Airport Similar Days Based on K-prototype Cluster and Grey Correlation Analysis

Considering similar air traffic control techniques for the present based on close historical dates is a good approach due to the unpredictability of weather and air traffic, as well as to increase controller efficiency. A K-prototype clustering technique and grey correlation analysis are proposed to discover similar days to address the problem of similar identification. Firstly, the weather and air traffic datasets are used to create a set of features broken down into numerical and categorical attributes. Secondly, the historical data are clustered using the K-prototype clustering, which is then paired with grey correlation analysis to identify days similar to the reference day and examine the traffic management initiatives employed on that day. Finally, the research uses actual weather information and aircraft schedules from Nanjing Lukou International Airport as examples. The outcomes demonstrate that the similar days picked by the model are representative and can serve as a foundation for airport controllers' decision-making.

ESG Fund Usage among Individual Investor Households: A Machine Learning–Based Behavioral Study

Interest in environmental, social, and governance (ESG) investing has increased substantially in recent years. Still, little research has demonstrated how ESG funds are being incorporated into portfolios by individual investor households. In this article, the authors explore a unique dataset containing the demographic and portfolio characteristics of more than five million households and identify those holding an ESG fund. Using an unsupervised machine learning technique called K-prototype clustering, the authors find five unique types of investors who have incorporated ESG mutual funds and/or ETFs into their portfolios. The authors then test to what extent incorporating ESG funds biases traditional portfolio construction decisions and find that ESG households have a strong growth tilt compared with similar non-ESG households. The research serves as a foundation for further study into the motivations behind, and portfolio implications of, implementing any of the identified ESG investment strategies.

Application of the k-Prototype Clustering Approach for the Definition of Geostatistical Estimation Domains

The definition of geostatistical domains is a stage in the estimation of mineral resources, in which a sample resulting from a mining exploration process is divided into zones that show homogeneity or minimal variation in the main element of interest or mineral grade, having geological and spatial meaning. Its importance lies in the fact that the quality of the estimation techniques, and therefore, the correct quantification of the mineral resource, will improve in geostatistically stationary areas. The present study seeks to define geostatistical domains of estimation for a mineral grade, using a non-traditional approach based on the k-prototype clustering algorithm. This algorithm is based on the k-means paradigm of unsupervised machine learning, but it is exempt from the one-time restriction on numeric data. The latter is especially convenient, as it allows the incorporation of categorical variables such as geological attributes in the grouping. The case study corresponds to a hydrothermal gold deposit of high sulfidation, located in the southern zone of Peru, where estimation domains are defined from a historical record of data recovered from 131 diamond drill holes and 37 trenches. The characteristics directly involved were the gold grade (Au), silver grade (Ag), type of hydrothermal alteration, and type of mineralization. The results obtained showed that clustering with k-prototypes is an efficient approach and can be used as an alternative or complement to the traditional methodology.

An efficient sharding consensus algorithm for consortium chains

The consensus algorithm is very critical in any blockchain system, because it directly affects the performance and security of the blockchain system. At present, the classic Practical Byzantine Fault Tolerance Algorithm (PBFT), which is mainly used in the consortium chain, will lead to system communication congestion and reduced throughput when the number of nodes increases, so the PBFT algorithm is not suitable for large-scale consortium chains. In response to the above problems, this paper proposes a new clustering-based sharding consensus algorithm (KBFT), which aims to ensure that the consortium chain takes into account decentralization, security and scalability. The KBFT algorithm first uses the K-prototype clustering algorithm to shard the nodes in the network according to mixed attributes, and second, disjoint transactions are used to reach consensus in parallel in different shards. Concurrently, the KBFT algorithm introduces a supervision mechanism and a node credit mechanism, which is used to supervise and score the behavior of the nodes and select the proxy nodes, which improves security. We discuss the choice of shard size with the help of the binomial probability distribution and analyze the probability that the system can successfully form a global block under different node failure probabilities. Finally, the proposed algorithm is evaluated through theoretical analysis and simulation experiments. Results show that the proposed algorithm achieves a marked improvement in scalability and throughput along with a marked reduction in communication complexity compared with the classic baseline algorithm PBFT in this field of study, which improves the operating efficiency of the system and simultaneously guarantees the security and robustness of the system.

Analysis of Freight Mode Characteristics on The Northern Coastline Route using Mixed Data Based Cluster Analysis

Due to the increase in the number of vehicles, the maintenance cost on north coast roads (Pantura route) increases because many of its parts are damaged, potholed, and other problems. Mode switching is expected to produce more efficiently, and grouping a mode's characteristics are proven to classify which products need to undergo a modal shift. In this study, a grouping of goods truck modes will be carried out based on the characteristics of the trip, the traveler, and the transportation system on the Northern coastline route to then provide policy recommendations for switching to another mode on the goods truck mode at the Northern coastline route with mostly possible characteristics. The method used for the grouping in this research is clustering analysis, particularly the k-prototype clustering method, and partitions around medoids because the data contains mixed variables, i.e., both categorical and numerical variables. Keywords: Cluster Analysis; Freight Transport; Mixed Data; Transportation

Investigation on typical occupant behavior in air-conditioned office buildings for South China’s Pearl River Delta

The excessive simplification of occupant behavior is considered as the most important factor that affects the uncertainty of building performance simulation, thus affects the reliability and generalizability of simulation-based design and forecast. In this paper, occupant behavior in air-conditioned office buildings of the Pearl River Delta (PRD) region was investigated and defined. Copies of 873 questionnaires about the occupant behavior in air-conditioned office buildings in the PRD region were collected to study the relationship between indoor environment quality and adaptive behaviors. Eight typical office occupant schedules were defined via K-means clustering method. A probability prediction model of cooling temperature set-point was established by using the Ordinal Logistic Regression method. According to the different control modes of air conditioning, window, blind and lighting equipment, four types of typical behavior patterns were proposed using the K-prototype clustering method, which could be developed into 20 typical occupant behavior styles of office buildings in the PRD region.

Retraction Note to: An efficient privacy preserving on high-order heterogeneous data using fuzzy K-prototype clustering

Retraction Note to: An efficient privacy preserving on high-order heterogeneous data using fuzzy K-prototype clustering

HEMClust: An Improved Fraud Detection Model for Health Insurance using Heterogeneous Ensemble and K-prototype Clustering

Health insurance plays an integral part of society's economic well-being; the existence of fraud creates innumerable challenges in providing affordable health care support for the people. In order to reduce the losses incurred due to fraud, there is a need for a powerful model to predict fraud on the data accurately. The purpose of the paper is to implement a more sophisticated technique for fraud detection using machine learning: HEMClust (Heterogeneous Ensemble Model with Clustering). The first phase of the model aims in improving the quality of claims data by providing effective preprocessing. The second stage addresses the overlapping instances in provider specialties by grouping them using k-prototype clustering. The final stage includes building the model using a heterogeneous stacking ensemble that performs classification on multiple levels, with four base learners in level 0 and a meta learner in level 1. The results were assessed using evaluation metrics and statistical tests such as Friedman and Nememyi to compare the performance of base classifiers against the proposed HEMClust. The empirical results show that the HEMClust produced 94% and 96% overall precision-recall rates on the dataset, which was an increase of 45% to 50% in the fraud detection rate for each class in the data.