Data Mining Process Research Articles

A Review of SDLCs for Big Data Analytics Systems in the Context of Very Small Entities Using the ISO/IEC 29110 Standard-Basic Profile

Context: A Systems Development Life Cycle (SDLC) is a model of phases-activities, roles, and products systematically used to develop software with functional expected quality. Although SDLC is widely applied to various software types, it remains unusual in Big Data Analytics Systems (BDAS). Objective: To address this issue, several SDLCs for BDAS have been proposed, along with comparative studies, to guide interested organizations in adapting them. This research seeks a lightweight, balanced, and feasible for small development teams or organizations, taking advantage of favorable characteristics of the international ISO standard. Method and Materials: This study describes the knowledge gap by reporting a comparative analysis of four relevant SDLCs. A selective research method was applied (CRISP-DM, TDSP, BDPL, and DDSL), focusing on alignment with the recent ISO/IEC 29110-basic profilestandard. The goal was to identify which SDLC contributes and fits better from a lightweight approach. Results: From the rigorous approach Cross Industry Standard Process for Data Mining (CRISP-DM) showed the highest alignment with the standard, for the agile approach it was Domino Data Science Lifecycle (DDSL) being the closest of the four. Team Data Science Process (TDSP) stood out as the most agile of those analyzed but fell short of the required results. BDPL, which manages another standard, was too rigorous and more distant. Conclusions: Research on new SDLC for Big Data Project Lifecycle (BDPL) has been practically nonexistent in software engineering from 2000 to 2023. Only BDPL was found in the academic literature, while the other three came from gray literature. Despite the relevance of this topic for BDAS organizations, no adequate SDLC was identified

Comparative Analysis of Multicriteria Inventory Classification and Forecasing: A Case Study in PT XYZ

One crucial aspect of supply chain management is inventory management. Inefficient inventory management can lead to various issues, such as product expiration, where a high number of items in the warehouse either have expired or are approaching expiration. This issue is experienced by a distribution SME in Indonesia, PT XYZ. Without such classifications, it becomes challenging to predict demand and manage stock levels efficiently. Therefore, the aim of this study is to classify inventory to identify the most important items to business and make a forecasting model of sales quantity to predict inventory replenishment using machine learning algorithms. To advance our research, we adopted the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology. For inventory classification, we conducted a hybrid approach that combined TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) and ABC analysis (A: high-value items, B: medium-value items, and C: low-value items). The data employed in this study comprised secondary data, including purchase orders, sales orders, and stock movement records. The result reveals that 11 of the total 383 items under class A are important items for business. After obtaining labels from the ABC Analysis, we proceed to train models using KNN, SVC, and Random Forest for predicting inventory classification. Notably, the Random Forest model showcased remarkable performance and outperformed the rest of the models, achieving an accuracy of 99.21%. For inventory forecasting ARIMA displays a competitive performance with RMSE value 5.305 and MAE value 3.476, indicating a relatively accurate prediction with lower forecasting errors than two other models

Dual-Language Sentiment Analysis: A Comprehensive Evaluating SVM, Logistic Regression, XGBoost, and Decision Tree Using TF-IDF On Arabic and English Dataset

Sentiment analysis (SA) is a growing area of study that straddles a number of disciplines, including machine learning, data mining, and natural language processing. It is focused on the automatic extraction of viewpoints presented in a certain text. Many studies have been conducted in the area of sentiment analysis because to its broad uses, particularly on texts in English, whereas other languages like Arabic have gotten less attention. The Arabic language presents several difficulties, such as its rich morphology and the difficulty of tracing words back to their original roots. Arabic comments have been analyzed and categorized into good and negative attitudes using a framework. With the aim of evaluating any tweet, opinion, purpose, or reputation, such as a university, company, mobile, and others, the research analyzes the comments made by users of the social networking site Twitter. It does this by using classification technology and machine learning, which are among the fundamental tasks of the data mining process used in the larger process, which is to explore knowledge . This search helps the user to access the evaluation of other users through their tweets and comments on the social networking site for an opinion immediately and automatically, and then the process of uploading and evaluating the opinions using appropriate algorithms for this purpose as(Decision Tree classifier DTC , XGboost, Logistic Regression LR, Support Vector Machine SVM )with Term Frequency-Inverse Document Frequency TF_IDF

Developing analytics-driven maintenance data mining processes: a design science approach

PurposeData mining has been well-applied by maintenance service providers in identifying data patterns and supporting decision-making. However, when applying data mining for analytics-driven maintenance, maintenance service providers often adopt data mining with unstructured “trial-and-error” approaches. In response, we have followed design science to develop a comprehensive approach to diagnosing the problems with the existing data mining processes model for analytics-driven maintenance service.Design/methodology/approachThis study conducted an in-depth case study with Siemens in the UK for data collection in order to apply a two-cycle build-and-evaluate design process. Based on the literature, the preliminary model is built. It is evaluated through the case company in the first cycle. In the second cycle, the model is refined based on the comments from the case company and then re-evaluated from both business management and information technology perspectives to ensure the applicability of the designed model in a real business environment.FindingsFirstly, this study identifies three main shortcomings in the existing data mining process models for analytics-driven maintenance. Secondly, this study develops the “Gear-Wheel Model”, with a customer-oriented cycle, a project planning cycle and a machine comprehension cycle, to overcome all these shortcomings simultaneously and provide improvement solutions. Thirdly, this study highlighted that the data mining processes for analytics-driven maintenance service need interactions from different functional departments and supports of successive data collection.Originality/valueThe study expands data mining analysis beyond a single business function to include interactions with other internal functions and external customers. It contributes to existing knowledge by focusing on the managerial aspects of data mining and integrating maintenance service providers with their business customers.

Klasifikasi Tingkat Depresi pada Anak dengan Menggunakan Algoritma Neural Network

Depression in children is an increasingly concerning mental health issue worldwide, with significant impacts on their social, academic, and emotional development. Early detection and prevention of depression are crucial for reducing long-term effects and improving children's quality of life. Conventional methods such as clinical observation and interviews have limitations, particularly regarding subjectivity and resource requirements. Therefore, this study develops a predictive model based on machine learning using a neural network algorithm to classify depression levels in children more accurately and promptly. The model utilizes data from various sources, including body humidity, body temperature, and step count, to detect signs of depression automatically and objectively. This research employs the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology, encompassing business understanding, data understanding, data preprocessing, modeling, model evaluation, and deployment stages. The dataset comprises 2001 entries with three main features, classified into three depression levels: normal, low, and high. The neural network used in the modeling demonstrates excellent performance, with accuracy nearly reaching 100% and loss values decreasing to almost zero. The model is then implemented in a web-based application designed to assist end users, such as parents and teachers, in classifying children's depression levels. Although the application does not yet have an integrated database, testing shows classification results consistent with the existing dataset, confirming its potential as a tool for early detection of depression in children.

A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective.

Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (e.g., social network analysis and recommender systems), computer vision (e.g., object detection and point cloud learning), and natural language processing (e.g., relation extraction and sequence learning), to name a few. With the emergence of Transformers in natural language processing and computer vision, graph Transformers embed a graph structure into the Transformer architecture to overcome the limitations of local neighborhood aggregation while avoiding strict structural inductive biases. In this paper, we present a comprehensive review of GNNs and graph Transformers in computer vision from a task-oriented perspective. Specifically, we divide their applications in computer vision into five categories according to the modality of input data, i.e., 2D natural images, videos, 3D data, vision + language, and medical images. In each category, we further divide the applications according to a set of vision tasks. Such a task-oriented taxonomy allows us to examine how each task is tackled by different GNN-based approaches and how well these approaches perform. Based on the necessary preliminaries, we provide the definitions and challenges of the tasks, in-depth coverage of the representative approaches, as well as discussions regarding insights, limitations, and future directions.

Forensic Discrimination of Lipstick Stains Using Attenuated Total Reflectance-Fourier Transform Infrared Spectroscopy and Pattern Recognition Techniques

Lipstick stains discovered on objects (such as drinking cups) may be utilized as evidence and/or lead in forensic investigations by chemical analysis. Hence, this study analyzed two brands of lipstick stains' organic composition on paper cups over 0, 24, and 48 h of exposure using attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR), coupled with pattern recognition techniques of principal component analysis (PCA) and linear discriminant analysis (LDA). Spectral analysis revealed several functional group differences between the two brands of lipstick, viz. Wardah (W) and Silkygirl (S) stains, particularly in the fingerprint region of 1800–650 cm−1. Application of PCA (variance of ≥ 70%) and LDA successfully provided the suitable means for categorically classifying (a) the different brands of lipstick, (b) the male and female volunteers, as well as (c) the different periods of exposure. The fact that the cross-validation correct classification rates for all the LDA models exceeded 90.0%, their suitability for forensic provenance application of lip stains appears statistically supported. Hence, such an approach to combine the non-destructive ATR-FTIR analysis with PCA and LDA is not only easy and cost-effective but also forensically relevant for enabling the data mining process for forensic intelligence.

A Case Study on the Data Mining-Based Prediction of Students’ Performance for Effective and Sustainable E-Learning

The study explores the application of data analytics and machine learning to forecast academic outcomes, with the aim of ensuring effective and sustainable e-learning. Technological study programs in universities often experience high dropout rates, which makes it essential to analyze and predict potential risks to reduce dropout percentages. Student performance prediction (SPP) offers potential benefits, including personalized learning and early interventions. However, challenges such as (1) data quality and availability and (2) incomplete and inconsistent data complicate this process. Moreover, to support the fourth Sustainable Development Goal (SDG), we focus on the quality of education. A case study approach is used using data mining techniques, particularly classification, regression, and clustering, to predict student performance. The case presented aims to predict risks and ensure academic success and quality. The cross-industry standard process for data mining (CRISP-DM) methodology is used to structure and guide the prediction process. The study shows that using data from student learning processes within an academic success prediction model and data mining can identify at-risk students.

Towards the Implementation of Heuristics Miner in .Net Framework

Process mining is an interdisciplinary field that bridges the gap between data mining and business process analysis. It revolves around the core concept of leveraging recorded event logs to automate the generation, validation, and refinement of process model. A majority of currently accessible process mining solutions are distributed in form of black box systems - software with no openly accessible source code - or as libraries for scripting languages like Python or R. In this sense, it is necessary to design and build an understandable foundation of a process mining library with the intention of presenting the possibility of incorporating process mining into many programs written in the language or aiding other programmers interested in the potential of such technologies. Therefore, this paper describes and demonstrates the usability of an advanced algorithm for process mining in the .NET platform, namely, the Heuristic miner for process modelling.

Comparison of Multiple Linear Regression and Random Forest Regression Models for House Price Prediction in Semarang City Using the CRISP-DM Method

The population density in Semarang City is increasing every year. This requires more potential land to build houses to accommodate the denser population. There are various kinds of house prices based on specifications in Semarang City. This requires the right prediction to get the desired house. This study implements and compares the performance of Multiple Linear Regression (MLR) and Random Forest Regression (RFR) models to predict house prices in Semarang City. The method used in this research is CRISP-DM (Cross-Industry Standard Process for Data Mining) as a data mining process. The data used in this research amounted to 9533 data with 8 variables obtained by web scraping. The data will go through a data preprocessing process then training the model. Next is the evaluation stage, which is carried out to measure the performance of the two models using evaluation metrics, namely R-Squared (prediction accuracy), MSE (Mean Squared Error), and RMSE (Root Mean Squared Error). The results of this study show that the MLR model obtained a prediction accuracy 61.1% with a training and testing data division ratio of 75%: 25%. While the RFR model produces a prediction accuracy 78.4% with a training and testing data division ratio of 90%: 10%. This shows that the RFR model is the best performing model. This research successfully applied the RFR model to the streamlit web framework. The final result of this research is a website that can be used by the public to predict house prices according to criteria in Semarang City.

Provisioning A Positive Cluster Associative Schema for Privacy Preservation in the Mining Paradigm

The considerable data age has seen an exponential rise in personal data due to the widespread use of mobile devices and the Internet. Since important information is extracted throughout the data mining process, there are significant privacy concerns regarding the network user data. Adding random noise to safeguard sensitive data while preserving certain statistical aspects is called privacy preservation, a novel paradigm that operates independently of the attackers' prior knowledge. Expanding upon the proposed technique for network user data and robust privacy, this research proposes a multiple cores positive cluster associative schema (PCAS-PP) with privacy preservation. During the data mining, you can better optimize data clustering and take advantage of the privacy leakage problem. Researchers do a thorough theoretical study and run simulations to assess our schema. The findings demonstrate that our schema is more accurate, efficient, and protects privacy than earlier schemas. Some other metrics like run time, F-measure and cluster ratio of three datasets are evaluated and compared.

Weather-aware energy management for unmannedaerial vehicles: a machine learning application with global data integration

This study introduces a machine learning (ML) framework to predict unmanned aerial vehicle (UAV) energy requirements under diverse environmental conditions. The framework correlates UAV flight patterns with publicly accessible weather data, to yield an energy management tool applicable to a wide range of UAV configurations. The model employs the Cross-industry standard process for data mining and advanced feature engineering, offering an in-depth analysis of meteorological factors and UAV energy demands. The study assesses several multi-regression linear and ML models, whereby ensemble models gradient boosting (GB) and eXtreme gradient boosting demonstrate superior performance and accuracy. Specifically, the GB model achieved a test mean absolute error (MAE) of 0.0395 V (V) for voltage, 0.808 A (A) for current, and 9.758 mA-hours (mAh) for discharge, with prediction accuracy of over 99.9% for voltage and discharge, and 97% for current, derived from the coefficient of determination (R2). A novel integration of real-world UAV logs and weather data underpins the development of a weather-aware ML prediction model for UAV energy consumption. Our framework is capable of concurrently predicting three components of energy and power with almost uniform accuracy, a feature not found in contemporary models. Empirical test flights show a discrepancy of only 0.005 W-hour (Wh) between total predicted and actual energy consumption. This work enhances both efficiency and safety in UAV operations. The resulting energy-predictive flight planning tool sets a new benchmark for artificial intelligence (AI) applications in intelligent automation for UAVs.

THE APPLICATION OF DATA MINING AND OLAP TECHNOLOGIES IN HEALTHCARE

The article examines the application of Data Mining and real-time Online Analytical Processing (OLAP) in healthcare. The calculation of analytical indicators and solving planning problems in healthcare are complex and multi-stage processes. The extraction of knowledge from large volumes of data accumulated in databases is referred to as Data Mining. Today, databases are measured in terabytes, containing strategically significant information. One of the most critical issues is determining methods for discovering important information within such vast amounts of data. Data Mining technology, by utilizing a set of analytical tools, helps to uncover relationships within large datasets and make predictions about future trends. Simply defined, Data Mining automatically identifies relevant patterns within databases. For many years, analysts manually recorded statistically significant relationships within databases. Today, Data Mining automates this process. The goal of Data Mining is to create decision-making models that predict future behavior based on the analysis of past actions. With the advent of computers and the rise of the digital information age, there have been changes in both the scale and complexity of existing problems in terms of analytical analysis. Advances in the storage, management, and examination of data have led to the emergence of a new field that promotes the development of bioinformatics and introduces analytical analysis and computational problems in the fields of biology and medicine. Keywords: Data Mining, OLAP, database, factor analysis, healthcare network, multidimensional models.

KnowVID-19: A Knowledge-Based System to Extract Targeted COVID-19 Information from Online Medical Repositories.

We present KnowVID-19, a knowledge-based system that assists medical researchers and scientists in extracting targeted information quickly and efficiently from online medical literature repositories, such as PubMed, PubMed Central, and other biomedical sources. The system utilizes various open-source machine learning tools, such as GROBID, S2ORC, and BioC to streamline the processes of data extraction and data mining. Central to the functionality of KnowVID-19 is its keyword-based text classification process, which plays a pivotal role in organizing and categorizing the extracted information. By employing machine learning techniques for keyword extraction-specifically RAKE, YAKE, and KeyBERT-KnowVID-19 systematically categorizes publication data into distinct topics and subtopics. This topic structuring enhances the system's ability to match user queries with relevant research, improving both the accuracy and efficiency of the search results. In addition, KnowVID-19 leverages the NetworkX Python library to construct networks of the most relevant terms within publications. These networks are then visualized using Cytoscape software, providing a graphical representation of the relationships between key terms. This network visualization allows researchers to easily track emerging trends and developments related to COVID-19, long COVID, and associated topics, facilitating more informed and user-centered exploration of the scientific literature. KnowVID-19 also provides an interactive web application with an intuitive, user-centered interface. This platform supports seamless keyword searching and filtering, as well as a visual network of term associations to help users quickly identify emerging research trends. The responsive design and network visualization enables efficient navigation and access to targeted COVID-19 literature, enhancing both the user experience and the accuracy of data-driven insights.

API comparison based on the non-functional information mined from Stack Overflow

When comparing similar APIs, developers tend to distinguish them from the aspects of functional details. At the same time, some important non-functional factors (such as performance, usability, and security) may be ignored or noticed after using the API in the project. This may result in unnecessary errors or extra costs. API-related questions are common on Stack Overflow, and they can give a well-rounded picture of the APIs. This provides us with a rich resource for API comparison. However, although many methods are offered for mining Questions and Answers (Q&As) automatically, they often suffer from two main problems: 1) they only focus on the functional information of APIs; 2) they analyze each text in isolation but ignore the correlations among them. In this paper, we propose an approach based on the pre-training model BERT to mine the non-functional information of APIs from Stack Overflow: we first tease out the correlations among questions, answers as well as corresponding reviews, so that one Q&A can be analyzed as a whole; then, an information extraction model is constructed by fine-tuning BERT with three subtasks—entity identification, aspect classification, and sentiment analysis separately, and we use it to mine the texts in Q&As step by step; finally, we summarize and visualize the results in a user-friendly way, so that developers can understand the information intuitively at the beginning of API selection. We evaluate our approach on 4,456 Q&As collected from Stack Overflow. The results show our approach can identify the correlations among reviews with 90.1% precision, and such information can improve the performance of the data mining process. In addition, the survey on maturers and novices indicates the understandability and helpfulness of our method. Moreover, compared with language models, our method can provide more intuitive and brief information for API comparison in non-functional aspects.

Identifications of False Positives Amongst Sodium(I) Cations in Protein Three-Dimensional Structures—A Validation Approach Extendible to Any Alkali or Alkaline Earth Cation and to Any Monoatomic Anion

Validation of the data deposited in the Protein Data Bank is of the upmost importance, since many other databases, data mining processes, and artificial intelligence tools are strictly grounded on them. The present paper is divided into two parts. The first part describes and analyzes validation methods that have been designed and used by the structural biology community. Everything began with the Ramachandran plot, with its allowed and disallowed types of backbone conformations, and evolved in different directions, with the inclusion of additional stereochemical features, distributions’ analyses of structural moieties, and scrutiny of structure factor amplitudes across the reciprocal lattice. The second part of the paper is focused on the largely unexplored problem of the high number of false positives amongst the sodium(I) cations observed in protein crystal structures. It is demonstrated that these false positives, which are atoms wrongly identified with sodium, can be identified by using electrostatic considerations and it is anticipated that this approach can be extended to other alkali and alkaline earth cations or to monoatomic anions. In the end, I think a global initiative, accessible to all volunteers and possibly overseen by the Protein Data Bank, should take the place of the numerous web servers and software applications by providing the community with a select few reliable and widely accepted tools.

Explorative Binary Gray Wolf Optimizer with Quadratic Interpolation for Feature Selection.

The high dimensionality of large datasets can severely impact the data mining process. Therefore, feature selection becomes an essential preprocessing stage, aimed at reducing the dimensionality of the dataset by selecting the most informative features while improving classification accuracy. This paper proposes a novel binary Gray Wolf Optimization algorithm to address the feature selection problem in classification tasks. Firstly, the historical optimal position of the search agent helps explore more promising areas. Therefore, by linearly combining the best positions of the search agents, the algorithm's exploration capability is increased, thus enhancing its global development ability. Secondly, the novel quadratic interpolation technique, which integrates population diversity with local exploitation, helps improve both the diversity of the population and the convergence accuracy. Thirdly, chaotic perturbations (small random fluctuations) applied to the convergence factor during the exploration phase further help avoid premature convergence and promote exploration of the search space. Finally, a novel transfer function processes feature information differently at various stages, enabling the algorithm to search and optimize effectively in the binary space, thereby selecting the optimal feature subset. The proposed method employs a k-nearest neighbor classifier and evaluates performance through 10-fold cross-validation across 32 datasets. Experimental results, compared with other advanced algorithms, demonstrate the effectiveness of the proposed algorithm.

Integrating Data Mining and Natural Language Processing to Construct a Melting Point Database for Organometallic Compounds.

As semiconductor devices are miniaturized, the importance of atomic layer deposition (ALD) technology is growing. When designing ALD precursors, it is important to consider the melting point, because the precursors should have melting points lower than the process temperature. However, obtaining melting point data is challenging due to experimental sensitivity and high computational costs. As a result, a comprehensive and well-organized database for the melting point of the OMCs has not been fully reported yet. Therefore, in this study, we constructed a database of melting points for 1,845 OMCs, including 58 metal and 6 metalloid elements. The database contains CAS numbers, molecular formulas, and structural information and was constructed through automatic extraction and systematic curation. The melting point information was extracted using two methods: 1) 1,434 materials from 11 chemical vendor databases and 2) 411 materials identified through natural language processing (NLP) techniques with an accuracy of 86.3%, based on 2,096 scientific papers published over the past 29 years. In our database, the OMCs contain up to around 250 atoms and have melting points that range from -170 to 1610 °C. The main source is the Chemsrc database, accounting for 607 materials (32.9%), and Fe is the most common central metal or metalloid element (15.0%), followed by Si (11.6%) and B (6.7%). To validate the utilization of the constructed database, a multimodal neural network model was developed integrating graph-based and feature-based information as descriptors to predict the melting points of the OMCs but moderate performance. We believe the current approach reduces the time and cost associated with hand-operated data collection and processing, contributing to effective screening of potentially promising ALD precursors and providing crucial information for the advancement of the semiconductor industry.

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.

Implementation of Random Forest with Synthetic Minority Oversampling Technique and Particle Swarm Optimization for Predicting Survival of Heart Failure Patients

Abstract. Heart failure is caused by a disruption in the heart’s muscle wall, which results in the heart’s inability to pump blood in sufficient quantities to meet the body’s demand for blood. The increasing prevalence and mortality rates of heart failure can be reduced through early disease detection using data mining processes. Data mining is believed to aid in discovering and interpreting specific patterns in decision-making based on processed information. Data mining has also been applied in various fields, one of which is the healthcare sector. One of the data mining techniques used to predict a decision is the classification technique. Purpose: This research aims to apply SMOTE and PSO to the Random Forest classification algorithm in predicting the survival of heart failure patients and to determine its accuracy results. Methods/Study design/approach: To predict the survival of heart failure patients, we utilize the Random Forest classification algorithm and incorporate data imbalance handling with SMOTE and feature selection techniques with PSO on the Heart Failure Clinical Records Dataset. The data mining process consists of three distinct phases. Result/Findings: The application of SMOTE and PSO on the Heart Failure Clinical Records Dataset in the Random Forest classification process resulted in an accuracy rate of 93.9%. In contrast, the Random Forest classification process without SMOTE and PSO resulted in an accuracy rate of only 88.33%. This indicates that the proposed method combination can optimize the performance of the classification algorithm, achieving a higher accuracy compared to previous research. Novelty/Originality/Value: Data imbalance and irrelevant features in the Heart Failure Clinical Records Dataset significantly impact the classification process. Therefore, this research utilizes SMOTE as a data balancing method and PSO as a feature selection technique in the Heart Failure Clinical Records Dataset before the classification process of the Random Forest algorithm.