Clustering Rules Research Articles

Forecasting Rate of Crime Using Machine Learning

Criminalities and predicting are indispensable when it comes to crime identification and prevention, and recognition of areas with a high probability of criminal occurrences, as well as simulation of crime scenes. Finally, and based on the methods of data mining, patterns can be obtained from large amount of unstructured data that can help in predicting future crimes. Crime is still a social issue that impacts the population on all the main aspects including quality of life, economic growth, and image of the nation, and thus, calls for more elaborate and effective systems and strategies for the safety of the population. With the help of the DM techniques proposed below, the goal is to design a system that is capable of identifying, studying, and these predicting types of crimes in certain areas. In particular, the current paper focuses on the methodological approaches of crime analysis and crime forecast. Thus, this work examined temporal and spatial features of crime to establish patterns and trends necessary to predict subsequent occurrences. Classification, clustering and association rule mining are utilized mainly in crime data classification process, in order to make distinctions and identify relationships between certain crime characteristics. Quantitative methods of analysis which include regression analysis, decision trees and artificial neural networks forecast future formulations of criminal incidences

Tooth point cloud resampling method based on divergence index and improved Euclidean clustering rule.

In endodontic therapy, 3D Cone Beam Computerized Tomography (CBCT) and oral scan fusion models allow exact root canal channels and guidance. However, the point cloud model from CBCT has few data points and poor model features, limiting 3D fusion with oral scan data. Our aim to build a sub-regional point cloud resampling method and evaluate the precision of merging it with three-dimensional oral scan data.
Approach: Two molars and four incisors were resampled for this investigation. Based on point cloud density and curvature, the rebuilt model was separated into the crown and cervical cavities. Using crown surface morphology, Divergence Index (DI) was employed to determine resampling points based on point dispersion. Improved Euclidean Clustering Rule (IECR) downsamples each point using its weight and joins the two halves using Iterative Nearest Neighbour (ICP) to create a complete resampled point cloud. After aligning with the oral scanning model, the maximum error, maximum distance, average distance, and other characteristics are calculated to assess resampling. Additionally, a cross-entropy kernel-based point cloud reconstruction depth selection method is given to determine the appropriate reconstruction depth.
Main results: Applying the DI-IECR technique reduces the average distance between the resampled tooth point cloud and the point cloud generated by the dental scanner by around 20%. The maximum error remains same to that of the widely used method. This study also demonstrates that the use of the DI-IECR approach guarantees the complete representation of the coronal characteristics of the resampled reconstructed 3D model, rather than excessively focusing processing resources on pertinent but insignificant areas.
Significance: Point cloud data and crown features are balanced using DI-IECR. When registered with the oral scan model, CBCT-generated point clouds are more accurate and timely, making them a better intraoperative navigation model.

Identifying attribute associations in fatal speeding crashes using latent class clustering and association rule mining

Speeding has been distinguished as one of the most frequent and persistent contributing factors and is a critical contributing factor to the degree of injury severity. In the United States, at least a quarter of nationwide annual fatal crashes during the last decade involved speeding. There is still a need for an overarching look at crashes involving speeding by considering a wider set of crashes, roadway, driver, and vehicle characteristics. Despite extensive research on speeding-related crashes, there is limited understanding of how collective variables in homogeneous crash clusters contribute to fatal speeding crashes. This paper addresses this gap by investigating these collective impacts using fatal crash data from the Fatality Analysis Reporting System (FARS). Using crash data from the 2015–2019 FARS repository, this study applies latent class clustering (LCC) to obtain homogeneous clusters of fatal speeding crashes, addressing the unobserved heterogeneity. Association rule mining (ARM) has been applied to homogeneous clusters to find hidden patterns. The finding of association rules, such as motorcycle speeding, single vehicle crashes during weekends, in dark, unlit conditions, etc. The results of this research and interpretative findings are expected to improve the knowledge of speeding-related crash mechanisms and to provide important insights on countermeasure development.

Supervised, Unsupervised Learning Methods in Data Mining: A Comprehensive Survey

Abstract: Data mining is the area of computational science consider as the subset of Artificial Intelligence, Machine Learning that concentrate on cognizing patterns and structures in data to promote learning, analyzing, and decision making beyond human interaction. In simplest term, data mining allows the user to feed data mining algorithms on an immense amount of data and then make the computer to make data-driven recommendations and decisions based on the input or training data. Data is the essential component of all business. Data mining with supervised and unsupervised methods is the key to unlock the value of business data and keep ahead of the competition. This paper presents a comprehensive survey on Data mining process, supervised, unsupervised methods, through a survey of literature considering the significant research areas using classification, clustering, and association rule mining.

Delivery service and online-and-offline purchasing for collaborative recommendations on retail cross-channels

ABSTRACT The delivery service business model is the final link in logistics for both online-and-offline business. Online-and-offline business models combine e-commerce and physical commerce, using online marketing techniques to drive consumption in physical channels. Delivery service and online-and-offline purchasing for collaborative recommendations on retail cross-channels are complex and cross-disciplinary problems of enterprise integration. This study implements two-stage data mining analytics for clustering and association rules analysis, to investigate Taiwan consumers’ (n = 2,209) preferences for delivery service. This process clarifies online-and-offline purchasing behaviours and preferences to find knowledge profiles/patterns/rules for cross-channel collaborative recommendations. Finally, theoretical and practical implications for methodology and enterprise are presented.

Uncovering patterns of disadvantage in student socioeconomic data using k-means clustering and association rule mining

This study employs a combination of k-means clustering and association rule mining to analyze socioeconomic data from 507 students at a community school in Udon Thani Province, Thailand, highlighting the pronounced economic inequalities impacting educational opportunities. By integrating these data mining techniques, the research categorizes students into four income-based clusters and identifies critical socioeconomic attributes influencing educational access and quality. The application of k-means clustering revealed four distinct economic categories within the student population, with the lowest income cluster significantly lacking in basic amenities such as air conditioning and agricultural vehicles, which are essential for their living and educational environments. Association rule mining was then applied to identify household attributes linked to the ‘very low’ income classification. Fourteen association rules were discovered, with support values ranging from 0.43 to 0.44, confidence levels between 0.81 and 0.82, and lift values consistently at 1.1. Key findings reveal that the absence of basic amenities such as air conditioning, agricultural vehicles, computers, and televisions are strongly associated with the lowest socioeconomic status. For instance, the rule {AirCondition=N, TV=N} => {Cluster=Very Low} had a support of 0.44, confidence of 0.81, and lift of 1.1, indicating households lacking these items have an 81% probability of being classified in the ‘very low’ income group. Notably, the presence of electricity did not correlate directly with higher income clusters, indicating that basic infrastructure access alone does not mitigate the broader socioeconomic challenges. These findings underscore the complex interplay between income levels and access to educational and basic living resources. The study’s implications are profound, advocating for targeted educational policies and interventions that address the nuanced needs of economically disadvantaged students, thereby enhancing their educational outcomes and socioeconomic mobility. Future research directions include broadening the dataset to multiple schools across different regions and conducting longitudinal studies to reveal long-term effects of socioeconomic factors on education.

Collaborative Filtering Recommendation System Using A Combination of Clustering and Association Rule Mining

A recommendation system helps collect and analyze user data to generate personalized recommendations for users. A recommendation system for movies has been implemented, considering the vast number of available films and the difficulty users face in finding movies that match their interests. One popular recommendation method is Collaborative Filtering (CF). Although widely applied, CF still has issues. Basic CF uses overlapping user data in evaluating items to calculate user similarity. This study aims to build a collaborative filtering recommendation system using clustering techniques to group users with similar interests into the same clusters. The next step in CF application is to gather recommendation candidate items by finding users with a high level of similarity to the target user. Subsequently, user pattern analysis is carried out by applying association rule mining to predict hidden correlations based on frequently watched items and the ratings given to those movies. This study uses rating data and movie data from the Movielens website. The evaluation of the recommendation results is measured using precision, recall, and f-measure. The evaluation results show that the proposed recommendation system achieves a hit rate of 95.08%, a precision of 81.49%, a recall of 98.06%, and an f-measure of 87.66%.

A Review on Data Mining Issues, Solution & Techniques

Data mining, the process of discovering patterns and knowledge from large datasets, has become a cornerstone of decision-making across various domains including business, healthcare, and finance. This paper reviews the current landscape of data mining applications, exploring the diverse techniques employed and the challenges faced. Key issues include data quality, privacy concerns, and the scalability of mining algorithms in the face of increasingly large and complex datasets. We discuss solutions to these challenges, such as advancements in data cleaning methodologies, privacy-preserving techniques, and the development of scalable algorithms. Additionally, we provide a comprehensive overview of current data mining techniques, including clustering, classification, and association rule mining, and evaluate their effectiveness in addressing real-world problems. The paper aims to provide understanding of both the potential and limitations of data mining, offering insights into future research directions and technological advancements needed to overcome existing hurdles.

An exploration of descriptive machine learning approaches for antimicrobial resistance: Multidrug resistance patterns in Salmonella enterica

Salmonellosis is one of the most common foodborne diseases worldwide, with the ability to infect humans and animals. Antimicrobial resistance (AMR) and, particularly, multidrug resistance (MDR) among Salmonella enterica poses a risk to human health. Antimicrobial use (AMU) regulations in livestock have been implemented to reduce AMR and MDR in foodborne pathogens. In this study, we used an integrated machine learning approach to investigate Salmonella AMR and MDR patterns before and after the implementation of AMU restrictions in agriculture in the United States. For this purpose, Salmonella isolates from cattle in the National Antimicrobial Resistance Monitoring System (NARMS) dataset were analysed using three descriptive models consisting of hierarchical clustering, network analysis, and association rule mining. The analysis showed the impact of the United States’ 2012 extra-label cephalosporin regulations on AMR trends and revealed a distinctive MDR pattern in the Dublin serotype. The results also indicated that each descriptive model provides insights on a specific aspect of resistance patterns and, therefore, combining these approaches make it possible to gain a deeper understanding of AMR.

A Proposal for Integrated Information System of Municipal Welfare Development Office Using Data Mining Methods for Decision Making Support

Technology's pervasive influence shapes contemporary communication, learning, and societal interactions. While its advancements bring benefits, they also pose challenges. This study addresses the complexities of technology in social welfare delivery, focusing on the Municipal Social Welfare and Development Office (MSWDO) of Placer, Surigao del Norte, Philippines. The current system of MSWDO faces operational hurdles particularly in managing social protection programs efficiently, leading to delays and frustrations among beneficiaries. Using a mixed-method approach, the study reviews the current provision through an online survey completed by the respondents selected by purposive sampling method. The findings show that respondents have a high level of agreement for the provision of an enhanced integrated information system. The proposed system, with the utilization of data mining techniques such as clustering, classification, and association rule method, can cater to Cash Assistance Budget Monitoring and Sectoral Records Digitalization. The recommendations prioritize Focal Persons, enhanced communication tactics, regular evaluations, and program designs that are adapted to meet local needs. The significance of digital solutions in optimizing social welfare delivery. By implementing recommended features, the MSWDO can enhance program efficiency, responsiveness, and impact, thereby better serving the community and maximizing resident welfare

Cluster synchronization control for the complex network with dynamic connection relations

AbstractIn this article, the cluster synchronization control for a complex dynamic network (CDN) with mutually coupled nodes subsystem (NS) and connection relations subsystem is investigated. The process of cluster synchronization is segmented into three dynamic continuous stages: first, the free movement, then the task‐oriented clustering, and finally the cluster synchronization. The control scheme, founded on the clustering nodes of CDN, is proposed, such that the cluster synchronization arises when clustering all the nodes into two different sub‐networks (SNs). This approach originates from the flight motion for a group of autonomous aircrafts. At a certain moment, free flight is interrupted, and all the aircrafts split into two SNs according to the given clustering rules. Then the two controlled SNs are required to achieve cluster synchronization, that is, every SN converges to the same in speed. In order to split all the nodes into two different SNs, a clustering algorithm according to the “central nodes” is proposed. Based on Lyapunov stability theory, by designing the suitable inner cluster links, the adaptive controller of NS for each SN is synthesized to guarantee the stability of the error system. It is shown that the eventual inner topology of each SN is displayed in the pre‐given form when the cluster synchronization achieves. Finally, the merits and effectiveness of the proposed control scheme are verified by a simulation example.

Investigating the contributing factors of crashes on interstate bridges in Louisiana using latent class clustering and association rule mining

Drivers on long bridges on interstates often face unique challenges, such as restricted lane width, inadequate shoulders, and a lack of clear zones for safe recoveries. Studies on understanding the factors that contribute to crash severity on such high-risk sections of interstates are limited. This research study applies latent class clustering (LCC) to detect homogeneous clusters while accounting for unobserved heterogeneity in a dataset of 10,036 crashes that occurred over a 6-year period (2015–2020) on eight selected bridges. Utilizing the LCC method, the research identifies four optimal clusters in bridge crashes, characterized by attributes such as ‘4-lane,’ ‘6-lane,’ ‘single-vehicle crashes,’ and ‘unknown driver.’ The Association Rule Mining (ARM) approach is used to identify the important collective factors to visible injury (KAB – fatal, severe and moderate) and property damage only (PDO or no injury). In Cluster 1 (4-lane), KAB and PDO crashes differ in collision type and visibility conditions, with rear-end crashes linked to KAB and sideswipe crashes to PDO. Cluster 2 (6-lane) shows similar distinctions but lacks specific lighting associations for PDO. In Cluster 3 (single-vehicle crashes), KAB involves moderate traffic and low visibility, while PDO has lower speed limits and non-dry surfaces. Cluster 4 (unknown driver), despite overrepresenting hit-and-run cases, underscores challenges in injury crash data collection in high-volume mobility scenarios. The discussions of the findings on the severity factors in this study are expected to help traffic safety engineers, policymakers, and planners to identify effective safety countermeasures on major elevated sections.

Design and Implementation of Teaching Quality Assessment System for Universities Based on Data Mining Algorithms

A teaching quality assessment system for universities based on data mining algorithms utilizes advanced analytical techniques to evaluate and enhance the effectiveness of teaching practices. By leveraging data mining algorithms, such as clustering, classification, and association rule mining, this system can analyze various educational data sources, including student performance metrics, course evaluations, and instructor feedback. This paper introduces Generative Pre-trained Data Analytics (GPDA) as a novel approach for assessing teaching quality in educational settings. GPDA leverages advanced data analytics techniques to predict teaching quality metrics, classify teaching quality data, and forecast various aspects of teaching effectiveness. Through comprehensive analysis and evaluation, GPDA demonstrates its accuracy, reliability, and versatility in capturing the complexities of teaching quality across diverse educational contexts. Through comprehensive analysis and evaluation, GPDA achieves a Root Mean Squared Error (RMSE) ranging from 0.152 to 0.190 and R-squared (R²) values ranging from 0.698 to 0.805, showcasing its accuracy and reliability in predicting teaching quality metrics across diverse educational contexts. Furthermore, strong positive correlations between the synthetic data generated by GPDA and real teaching quality data, with correlation coefficient values ranging from 0.87 to 0.92, validate the fidelity of GPDA-generated synthetic data.

Unsupervised machine learning approach for tailoring educational content to individual student weaknesses

By analyzing data gathered through Online Learning (OL) systems, data mining can be used to unearth hidden relationships between topics and trends in student performance. Here, in this paper, we show how data mining techniques such as clustering and association rule algorithms can be used on historical data to develop a unique recommendation system module. In our implementation, we utilize historical data to generate association rules specifically for student test marks below a threshold of 60%. By focusing on marks below this threshold, we aim to identify and establish associations based on the patterns of weakness observed in the past data. Additionally, we leverage K-means clustering to provide instructors with visual representations of the generated associations. This strategy aids instructors in better comprehending the information and associations produced by the algorithms. K-means clustering helps visualize and organize the data in a way that makes it easier for instructors to analyze and gain insights, enabling them to support the verification of the relationship between topics. This can be a useful tool to deliver better feedback to students as well as provide better insights to instructors when developing their pedagogy. This paper further shows a prototype implementation of the above-mentioned concepts to gain opinions and insights about the usability and viability of the proposed system.

Using Data Mining Techniques to Develop Climate Change Mitigation and Adaptation Strategies in Nigeria

Climate change is a severe and growing challenge facing Nigeria, with significant impacts on the country's economy, environment, and society. To cope with this challenge, there is a need for climate change mitigation and adaptation strategies that are evidence-based and tailored to the country's unique vulnerabilities and opportunities. This study aimed to develop such strategies using data mining techniques. A range of climate and non-climate data sources were explored to identify key drivers of climate change in Nigeria and their associated impacts on different sectors, such as agriculture, water resources, and energy. Subsequently, data mining algorithms, including decision trees, clustering, and association rule mining, were applied to model and analyze the complex relationships between these drivers and their impacts on the sectors. The study found that a combination of mitigation and adaptation measures could be effective in reducing the severity of climate change impacts in Nigeria. These measures include promoting the use of renewable energy sources, improving water-use efficiency, and developing climate-smart agricultural practices. The data mining techniques used in this study proved useful for identifying these measures and for predicting their effectiveness under different scenarios. The results of this study provide important insights to policymakers and practitioners in Nigeria and other countries facing similar climate change challenges. It also highlights the potential of data mining techniques for developing climate change mitigation and adaptation strategies that are evidence-based, effective, and tailored to specific local contexts. Overall, this study contributes to the growing body of literature on leveraging data mining and machine learning techniques for addressing complex environmental and societal challenges.

The typical AV accident scenarios in the urban area obtained by clustering and association rule mining of real-world accident reports

Automated Vehicles (AVs) based on a collection of advanced technologies such as big data and artificial intelligence have opened an opportunity to reduce traffic accidents caused by human drivers. Nevertheless, traffic accidents of AVs continue to occur, which raises safety and reliability concerns about AVs. AVs are particularly vulnerable to accidents on urban roads than on highways due to various dynamic objects and more complex infrastructure. Several studies proposed a scenario-based approach of experimenting with the response of AVs to specific situations as a way to test their safety. Reliable and concrete scenarios are necessary to test AV safety under critical conditions accurately. This study aims to derive a typical accident scenario for evaluating the safety of AVs, specifically in urban areas, by analysing collisions reported by the DMV of California, USA. We applied a hierarchical clustering method to find groups of similar reports and then executed association rule mining on each cluster to correlate between accident factors and collision types. We combined statistically significant association rules to constitute a total of 14 scenarios that are described according to an adapted PEGASUS framework. The newly obtained scenarios exhibit significantly different accident patterns than the typical Human-driven Vehicles (HVs) in urban areas reported by National Highway Traffic Safety Administration. Our discovery urges AV safety to be tested reliably under scenarios more relevant than the existing HV accident scenarios.

A Consumer Behavior Analysis Framework toward Improving Market Performance Indicators: Saudi’s Retail Sector as a Case Study

Studying customer behavior and anticipating future trends is a challenging task, as customer behavior is complex and constantly evolving. To effectively anticipate future trends, businesses need to analyze large amounts of data, use sophisticated analytical techniques, and stay up-to-date with the latest research and industry trends. In this paper, we propose a comprehensive framework to identify trends in consumer behavior using multiple layers of processing, including clustering, classification, and association rule learning. The aim is to help a major retailer in Saudi Arabia better understand customer behavior by utilizing the power of big data analysis. The proposed framework is presented as being generalized to gain insight into the generated big data and enable data-driven decision-making in other relevant domains. We developed this framework in collaboration with a large supermarket chain in Saudi Arabia, which provided us with over 1,000,000 sales transaction records belonging to around 30,000 of their loyal customers. In this study, we apply our proposed framework to those data as a case study and present our initial results of consumer clustering and association rules for each cluster. Moreover, we analyze our findings to figure out how we can further utilize intelligence to predict customer behavior in clustered groups.

Rule breaker boron clusters: a new class of hypoelectronic osmaborane clusters [(Cp*Os)2BnHn] (n = 6-10).

Since the pioneering electron counting rule for borane clusters was proposed by Wade, the structures and bonding of boron clusters and their derivatives have been elegantly rationalised. However, this rule and its modified versions faced problems explaining the electronic structures of less spherical deltahedra, unlike the core geometries of borate dianions [BnHn]2- (n = 6-12). Herein, we report the isolation of a series of osmaborane clusters [(Cp*Os)2BnHn], 1-5, (n = 6-10) by the thermolysis of an in situ generated intermediate, obtained from the rapid condensation of [Cp*OsBr2]2 and [LiBH4·THF], with [BH3·THF] or [BH3·SMe2]. Interestingly, all these clusters show unusual less spherical deltahedral shapes that can be generated from canonical [BnHn]2- (n = 8-12) shapes by doing diamond-square-diamond (DSD) rearrangements. The DSD rearrangements led to the generation of higher degree vertices, which are occupied by Os atoms and also generated Os-Os bonds in these clusters. Theoretical calculations revealed that these Cp*Os⋯OsCp* interactions in clusters 1-5 played a crucial role in their structural shape and electron count. These less spherical deltahedral clusters are rare, and most significantly, clusters 1-5 with (n-1) skeleton electron pairs (SEPs) do not follow Wade-Mingos electron counting rules and can be classified as hypoelectronic closo clusters.

Improvised Software Code Comprehension Using Data Mining

Millions of lines of code are used to create the modern software applications, which are more complicated in terms of their structure, behaviour, and functionality. The rapid advancement of supporting and enabling technologies, for example, is one reason why the development life cycles of these applications show a propensity to get shorter. As a result, a growing amount of the expense associated with software development moves from the generation of new artefacts to their adaption. Understanding the layout, functionality, and behaviour of current code artefacts is essential to this activity. The task of understanding code is crucial to software maintenance. We employed data mining techniques including clustering, classification, and associative rules to improvise software code comprehension

Entropy-Based Thunderstorm Imaging System With Real-Time Prediction and Early Warning

A combination of the sample entropy and the artificial intelligence (AI) would hopefully bring progress to the smart thunderstorm detection. In this paper, we establish an entropy-based thunderstorm point charge imaging system with the data clustering, wherein data are ultra-reliable and have low-latency three-dimensional atmospheric electric field (3DAEF) values. In particular, a high resolution 3DAEF sensor with the single-axis rotary vane is developed to measure the time sequence signal of the 3DAEF. The signal is first denoised, and then decomposed into multiple groups of branch data with the same number of samples. In order to break through the limitations of existing clustering rules, we propose a 3DAEF signal reconstruction method based on entropy intervals. By reconstructing the branch data, multiple time-scale data are formed. Finally, the curve fitting of the data is performed to realize the imaging after clustering the data. Experimental results suggest that the imaging error after the clustering is reduced by about 2.33%. Comparisons with radar charts show that the proposed system can effectively image the point charge moving paths.