Data Mining Methods Research Articles

Analysis on the Growth of Shared Bike Users Based on Random Forest Model

By analyzing the data set of hourly rental of shared bikes in Washington, D. C., this paper explores how to achieve the growth of shared bike users based on the methods of data mining and visual exploration. In this paper, machine learning models such as ridge regression, lasso regression, support vector machine regression and random forest regression are mainly selected to predict the needs of shared bike users, and then the random forest regression is verified as the optimal model. The result of this article explores the reasonable scheduling of auxiliary resources in the shared bike industry, improves the utilization rate of bicycle resources.

Detecting loss of excitation condition of synchronous generator in the presence of unified power flow controller based on data mining method

Loss-of-excitation (LOE) conditions may cause devastating effects on both the generator and power system. If LOE is not meticulously detected, two dangerous events may emerge: 1. unnecessary trip signal, 2. not detecting this abnormal condition or detecting it with time delay. Both mentioned flaws have considerable harmful consequences on the generator and power system. Conventional techniques for detecting LOE conditions are based on impedance measurement. The presence of flexible alternating current transmission (FACT) system devices can considerably affect the impedance characteristic of the system and as a result, the operation of impedance-based relays. This paper simulates LOE and stable power swing (SPS) conditions causing failures and errors in the LOE protection in the presence or absence of a unified power flow compensator (UPFC), and parameters with different behaviors are determined. Then, the most sensitive parameters are combined using an intelligent method. The single parameter, achieved from a combination of features in the previous process, is applied to a learning vector quantization (LVQ) neural network. The LVQ is a type of artificial neural network that is based on a prototype supervised learning classification algorithm and trained its network through a competitive learning algorithm. The simulation results show that, in a single machine infinitive bus (SMIB) test system, R-X directional scheme has 2 mal-operations and the proposed algorithm has no mal-operation without UPFC in the system. With UPFC in the system, the R-X directional scheme has four mal-operations and the proposed algorithm has no mal-operation. In the IEEE 9-bus test system, the R-X directional scheme has five mal-operations and the proposed algorithm has no mal-operation. Moreover, applying the proposed algorithm, LOE is detected very quickly in the presence or absence of the UPFC in the system and this approach prevents electrical and mechanical stresses enforced to the machine and power system. © 2017 Elsevier Inc. All rights reserved.

Klasterisasi Obat Berdasarkan Tipe dan Komposisi Sejenis pada Bagian Farmasi Rumah Sakit Queen Latifa

One important element in maintaining and improving the quality of healthcare services is the availability of adequate medication. Drugs are a crucial component used in the provision of healthcare services, and the expenses associated with them constitute a significant portion of overall healthcare costs. The implementation of data mining can aid in analyzing drug usage to obtain information that can be utilized for planning and controlling drug inventory, with one of the methods being the utilization of the K-Means algorithm. The K-Means algorithm is the most popular and widely used clustering method in data mining. This research aims to facilitate pharmacy personnel in identifying groups of drug types with similar characteristics and compositions. As a result, the categorization of a large number of drugs can be performed more efficiently and accurately. Moreover, with the grouping of drugs based on similar characteristics and compositions, pharmacy personnel can easily monitor the availability of specific medications and take appropriate actions in managing drug supplies at the hospital.

Analysis and Implementation of the Apriori Algorithm for Strategies to Increase Sales at Sakinah Mart

Sakinah Mart is a retail business that focuses on determining the layout of goods based on perceptions and implementing a discount system for specific items, but without offering bundling packages. This research aims to provide recommendations using the apriori algorithm as a decision-making tool for analyzing the layout of goods and bundling packages. The apriori algorithm is a data mining technique used to discover association rules and analyze customer purchases, specifically identifying the likelihood of customers buying item X along with item Y. The algorithm consists of two main components: support and confidence. The research applies the Cross-Industry Standard Process for Data Mining (CRISP-DM) method, utilizing the apriori algorithm to analyze sales transaction data. The dataset includes 2000 sales transactions with two attributes, resulting in the identification of 2 and 3 itemsets. The findings include 16 rules with a minimum support value of 42% and a minimum confidence of 85% for the layout of goods. For bundling packages, 5 rules with a minimum support value of 40% and a minimum confidence of 90% were generated. These results offer valuable recommendations to the company, using the apriori algorithm for analyzing the layout of goods and bundling packages.

A hybrid data-driven approach for the analysis of hydrodynamic lubrication

The application of data mining technology has intensively advanced tribology research. While recent lubrication studies have highlighted the importance of data mining, researchers have not fully bridged the gap between massive lubrication data and intrinsic lubrication mechanisms. Thus, by revisiting lubrication modelling from the data-driven and physics-informed perspectives, we aim to construct a hybrid approach for hydrodynamic lubrication classification and prediction, where data-driven methods are combined with physics-informed approaches to achieve a fast and accurate prediction of the hydrodynamic lubrication scenario. Our approach will spur the application of data mining methods in lubrication studies.

Approaching nearly zero energy of PV direct air conditioners by integrating building design, load flexibility and PCM

The energy matching of PV driven air conditioners is influenced by building load demand and PV generation. Merely increasing energy performance of building or PV capacity separately may improve the energy balance on a large time resolution, the real-time energy mismatching problem is still serious. In this study, a coordinated optimization method of PV capacity, building design, and load flexibility is proposed for improving the real-time energy matching of PVAC system. Then, a methodology integrating data mining method (XG Boost) and parametric simulation was developed to identify the determinant parameters of PV system and building design, exploring feature importance and correlations. The results of XG Boost indicate that the PV capacity, shape factor, and SHGC are the most critical factors. Finally, based on the optimized building design, the PCM layer was applied to improve the real time energy matching. To achieve a goal of 90 % ZEP, the PCM capacity can be decreased by 50.4 % and 62.8 % in Guangzhou and Shanghai in the optimized building. Moreover, the PV capacity can be reduced by 23 % in Guangzhou. The findings of this study provide practical guidance for designing PVAC system coupling with building design and energy storage devices.

Financial Decision Management of Enterprise Cloud Accounting Based on Big Data Technology

Abstract As an inevitable trend of the development of the times, this paper explores the application of big data technology in enterprise financial decision-making and constructs a complete process of enterprise financial management based on data mining. The improved k-Means algorithm is used to complete the clustering analysis of financial data, and the CAP algorithm is applied to the identification and classification of financial problems to realize the early warning of the financial crisis. Combining analysis and early warning, the financial decision management system in enterprise cloud accounting is constructed using the ID3 algorithm. Company H, a real estate enterprise, was selected as a research case and analyzed by collecting financial data and using data mining methods. The profitability, solvency, operations, growth, and cash capacity scores for Company H in 2021 are 11.19, 4.24, 4.94, −0.56, and −0.48, respectively. The changes in Company H’s profitability, solvency, and operations are relatively stable from 2013-2019.

Would it be better for partition prediction of heavy metal concentration in soils based on the fusion of XRF and Vis-NIR data?

Heavy metal (HM) contamination in soil necessitates effective methods to diagnose suspected contaminated areas and control rehabilitation processes. The synergistic use of proximal sensors demonstrates significant potential for rapid detection via accurate surveys of soil HM pollution at large scales and high sampling densities, and necessitates the selection of appropriate data mining and modeling methods for early diagnosis of soil pollution. The aim of this study is to evaluate the performance of a subarea model based on geographically partitioned and global models based on high-precision energy dispersive X-ray fluorescence (HD-XRF) and visible near-infrared (vis-NIR) spectra using a random forest model for predicting soil Cu and Pb concentrations. A total of 166 soil samples are acquired from a contaminated plot in Baiyin, Gansu Province, China. The soil samples are subjected to HM analysis and proximal sensor scanning in a laboratory. Vis-NIR spectral data are preprocessed using the Savitzky Golay (SG) and first-order derivative with Savitzky Golay (SGFD) methods. The results show that for predicting Cu and Pb concentrations in soil, the subarea models performs better than the global models in terms of quantitative prediction, based solely on individual HD-XRF data. For the subarea and global models, the R2 values are 0.961 and 0.981, respectively; the RMSE values are 27.8 and 79.6, respectively; and the RPD values are 4.96 and 7.38, respectively. However, making use of the random forest algorithm trained with data fusion obtained from the HD-XRF and vis-NIR sensors, the global model achieves the best predictions for Cu and Pb concentrations via HD-XRF + vis-NIR (SGFD) and HD-XRF + vis-NIR (SG), respectively. The results will provide a new perspective for modeling approaches to rapidly invert HM concentrations based on proximal sensor data fusion within a large scope of the study area.

Machine learning prediction model based on enhanced bat algorithm and support vector machine for slow employment prediction.

The employment of college students is an important issue that affects national development and social stability. In recent years, the increase in the number of graduates, the pressure of employment, and the epidemic have made the phenomenon of 'slow employment' increasingly prominent, becoming an urgent problem to be solved. Data mining and machine learning methods are used to analyze and predict the employment prospects for graduates and provide effective employment guidance and services for universities, governments, and graduates. It is a feasible solution to alleviate the problem of 'slow employment' of graduates. Therefore, this study proposed a feature selection prediction model (bGEBA-SVM) based on an improved bat algorithm and support vector machine by extracting 1694 college graduates from 2022 classes in Zhejiang Province. To improve the search efficiency and accuracy of the optimal feature subset, this paper proposed an enhanced bat algorithm based on the Gaussian distribution-based and elimination strategies for optimizing the feature set. The training data were input to the support vector machine for prediction. The proposed method is experimented by comparing it with peers, well-known machine learning models on the IEEE CEC2017 benchmark functions, public datasets, and graduate employment prediction dataset. The experimental results show that bGEBA-SVM can obtain higher prediction Accuracy, which can reach 93.86%. In addition, further education, student leader experience, family situation, career planning, and employment structure are more relevant characteristics that affect employment outcomes. In summary, bGEBA-SVM can be regarded as an employment prediction model with strong performance and high interpretability.

Skill analysis of library and information science professionals

This paper investigated professional skills for library and information science (LIS) professionals based on the American Library Association (ALA) job website. The study identified job categories and library types, examined required soft skills and professional skills, and analyzed the relationships between professional skills and job categories, and the relationships between professional skills and library types as well. Data mining, subject analysis, and information visualization methods were used in the study. The findings of this study show that the LIS field demands a wide range of comprehensive professional skills. In total, over 160 distinct professional skill requirements and 24 skill themes were uncovered. Across various LIS job categories, an average of 8.84 professional skill themes per job category was found to be necessary for success. Among these skill themes, certain ones stood out as particularly in-demand, including: Productivity Software, MARC Standards and Guidance, Integrated Library Automation, Programming, and Data Analysis. Furthermore, it was observed that the specific professional skill requirements varied across different types of libraries. Notably, Academic/Research (College/University) libraries and Public Libraries stood out as two types that demanded a broader range of professional skill themes compared to other types of libraries. The findings of this research study can inform library and information science researchers, educators, and professionals to better understand the LIS professional skill requirements, improve existing curricular systems, and develop new courses to meet the job market needs.

Financial Risk Prediction based on Time Series

In this paper, the data mining method based on time series is applied to financial risk prediction, the corresponding model is established, and the predictive ability of the model is tested according to the real financial data of K company. The actual test results show that the time series method is suitable for the prediction of financial data with regular periodic changes, and it has high accuracy.

MR-AT: Map Reduce based Apriori Technique for Sequential Pattern Mining using Big Data in Hadoop

One of the most well-known and widely implemented data mining methods is Apriori algorithm which is responsible for mining frequent item sets. The effectiveness of the Apriori algorithm has been improved by a number of algorithms that have been introduced on both parallel and distributed platforms in recent years. They are distinct from one another on account of the method of load balancing, memory system, method of data degradation, and data layout that was utilised in their implementation. The majority of the issues that arise with distributed frameworks are associated with the operating costs of handling distributed systems and the absence of high-level parallel programming languages. In addition, when using grid computing, there is constantly a possibility that a node will fail, which will result in the task being re-executed multiple times. The MapReduce approach that was developed by Google can be used to solve these kinds of issues. MapReduce is a programming model that is applied to large-scale distributed processing of data on large clusters of commodity computers. It is effective, scalable, and easy to use. MapReduce is also utilised in cloud computing. This research paper presents an enhanced version of the Apriori algorithm, which is referred to as Improved Parallel and Distributed Apriori (IPDA). It is based on the scalable environment referred as Hadoop MapReduce, which was used to analyse Big Data. Through the generation of split-frequent data regionally and the early elimination of unusual data, the proposed work has its primary objective to reduce the enormous demands placed on available resources as well as the reduction of the overhead communication that occurs whenever frequent data are retrieved. The paper presents the results of tests, which demonstrate that the IPDA performs better than traditional apriori and parallel and distributed apriori in terms of the amount of time required, the number of rules created, and the various minimum support values.

Prediction of Graduation for Students at the ISB Atma Luhur Faculty of Information Technology Using the C4.5 Algorithm

Higher Education is a level of education after secondary education which includes diploma programs, undergraduate programs, master programs, doctoral programs, professional programs, and specialist programs organized based on the culture of the Indonesian nation. Student graduation is one of the important factors to improve university accreditation. Students who graduate above 5 years and the number of students who drop out are important indicators in determining accreditation which then causes the difficulty of accrediting a college to rise. This research aims as an early warning for students who graduate on time and graduate late from the Faculty of Information Technology, Institute of Science and Business Atma Luhur using the C4.5 decision tree algorithm by implementing the Cross-Industry Standard Process for Data Mining (CRISP- DM) method. The initial data of this research amounted to 1,015 which was taken through a query in the database of the Atma Luhur Institute of Science and Business. However, the data that will be used becomes 694 after preprocessing due to the large number of record contents that do not have a graduation year, with a total of 641 graduates graduating on time and 53 graduates graduating late. Based on the application of the model using the C4.5 decision tree algorithm and the Confusion Matrix method, the accuracy is 93.94%, Recall is 98.59%, and Precision is 95.03%. So it can be concluded that the C4.5 decision tree algorithm is the most effective algorithm for predicting student graduation, because it has a high level of accuracy.

Data Mining Technique for Breast Cancer Prediction using Fuzzy Theory

In order to find a reliable approach of breast cancer prediction, Data mining methods are used in the studies provided in this article. This study compares multiple patient clinical data in order to find a reliable model that can predict the occurrence of breast cancer. In this article, the support vector machine (SVM), artificial neural network (ANN), naive bayes classifier, and AdaBoost tree are used as four data mining methods. Furthermore, since it has such a significant impact on the efficacy and efficiency of the learning process, feature space is extensively examined in this work. Combining PCA with other data mining algorithms that use a PCA-like technique to compress the feature space is recommended. This hybrid is intended to assess the effect of feature space reduction. Wisconsin Breast Cancer Database (1991) and Wisconsin Diagnostic Breast Cancer (1995) are two frequently used test data sets that are used to assess the effectiveness of these algorithms. To calculate each model's test error, the method of 10-fold cross-validation is used. The findings of this research show a thorough trade-off between these tactics and also provide a thorough assessment of the models. In practical applications, it is anticipated that feature identification results would help to avoid breast cancer for both doctors and patients.

Driver Analysis of High-end Sausage Brands in Shanghai City

Focusing on the five mainstream brands and CP Brand, this paper aims to analyze the target population, product demand and market pattern of the high-end sausage products in Shanghai. This study utilizes a variety of survey methods, three-stage sampling method, and questionnaire survey on the resident population aged 18-60 years old in Shanghai as the target population to collect data. It mainly utilizes a variety of quantitative analysis and data mining methods to aid CP in refining the strategy of hot item development. Through the analysis of the market pattern, the problems in CP Brand's customer development and customer retention capabilities, market positioning, and the driving force of brand competition are found. Through the analysis, the conclusion is as follows: CP Sausage's product positioning is not clear in consumers' mind, and the product characteristics are not visible. In this regard, CP Brand should cultivate the advantages of the brand independent of the existing brands in the market, and develop the irreplaceable product status of the brand. Finally, it should make the brand's high-end sausage products show up more frequently in front of the consumers so that the consumers can know more about its products, and then it can get into the market quickly and gain a market share.

Examining Seasonal Changes in Light-Vehicle Traffic Volume on Freeways Under Extreme Weather Conditions: A Combination of Temporal Statistical and Data Mining Non-Parametric Techniques

Today, with the increasing changes in weather patterns and the huge amount of data related to weather and traffic in different parts of the freeway network, the use of data mining methods to quantify the impact of weather on traffic flow is inevitable. The main objective of this study is to present a geostatistical method for computing and analyzing the effects of base and extreme cases of weather variables on light-vehicle traffic volumes on freeways, with an emphasis on temporal changes on different days of the week and between daytime and nighttime. In the proposed method for statistical analysis, the parametric test of two-way analysis of variance was used. In the following, with the development of a nonparametric method based on the classification and regression tree (CART) decision tree algorithm, the weather-related parameters with the greatest effect on traffic volumes were investigated separately for different seasons. For this purpose, nine years of statistics covering traffic and weather data for the studied freeway were analyzed. The computational results show that a fall in temperature of more than 35% on weekdays during the cold season and the parameters of horizontal visibility and rainfall during the day and temperature during the night in the spring cause a reduction of traffic volume of more than 45%. This study has shown that the combination of data-driven parametric and nonparametric data mining techniques is effective for traffic managers in planning and traffic control under extreme weather conditions. In this regard, an adverse weather conditions dynamic message sign (AWCDMS) framework was proposed as a practical way to warn drivers of adverse weather.

Penerapan Algoritma C.45 Dalam Pengklasifikasian Data Penjualan Gerai Makanan Cepat Saji Berbasis Website

With the development of technology, there are many methods that can be used to analyze various kinds of problems, both in the world of education, social and even the business world. One method that can be used is the data mining method. Fast food is one example of a business that is being built by many people today, especially in the city of Batam. With so many fast food outlets in the city of Batam, this study aims to classify the types of food that are in demand and not in demand in the city of Batam. To assist the writer in classifying the best-selling and not-selling food types, in this study the authors used the data mining method, namely applying the C.45 Algorithm approach. Apart from using the C.45 Algorithm to test the calculation results, the author uses a website-based information system. From the research that has been carried out, the results obtained are that the best-selling food for children is the Original Burger (BO) and for adults the best-selling type of food is Kebab (K), while the less popular type of food for all ages is Burger Crispy.

Student Performance Prediction

Abstract: Assessing student’s learning performance is a fundamental aspect of evaluating educational systems, playing a pivotal role in addressing challenges within the learning process and measuring learning outcomes. The emergence of educational data mining (EDM) as a research field has harnessed the power of data and knowledge to enhance education systems. EDM involves the development of techniques to analyze data collected from educational environments, offering a more comprehensive understanding of students and facilitating improvements in educational outcomes. The integration of machine learning (ML) technology has witnessed substantial growth, enabling researchers and educators to leverage data mining insights to predict and simulate educational processes, including success rates, dropouts, and more. This research paper explores the analysis of students' performance through data mining methods. It employs classification technique to discern the early-stage impact on GPA. In the classification methodology, various machine learning models are experimented with to predict student performance in the early stages, incorporating diverse features such as course grades and admission test scores. The paper employs different assessment metrics to evaluate model performance. The findings underscore the potential of educational systems to proactively address the risk of student failures during their initial stages of education

Enhancing Multimodal Information Retrieval Through Integrating Data Mining and Deep Learning Techniques

Multimodal information retrieval, the task of re trieving relevant information from heterogeneous data sources such as text, images, and videos, has gained significant attention in recent years due to the proliferation of multimedia content on the internet. This paper proposes an approach to enhance multimodal information retrieval by integrating data mining and deep learning techniques. Traditional information retrieval systems often struggle to effectively handle multimodal data due to the inherent complexity and diversity of such data sources. In this study, we leverage data mining techniques to preprocess and structure multimodal data efficiently. Data mining methods enable us to extract valuable patterns, relationships, and features from different modalities, providing a solid foundation for sub- sequent retrieval tasks. To further enhance the performance of multimodal information retrieval, deep learning techniques are employed. Deep neural networks have demonstrated their effectiveness in various multimedia tasks, including image recognition, natural language processing, and video analysis. By integrating deep learning models into our retrieval framework, we aim to capture complex intermodal dependencies and semantically rich representations, enabling more accurate and context-aware retrieval.

Medication rule of traditional Chinese medicine in the treatment of plateau hypoxia based on data mining.

The development of traditional Chinese medicine (TCM) in the plateau area is relatively backward. There is a lack of system to analyze the effects of the special environment of plateau low pressure and hypoxia on human meridians qi and blood, as well as the etiology and pathogenesis of plateau hypoxic diseases. To analyze the composition rules of anti-hypoxia TCM formulation with data mining methods. The experimental literatures related to high altitude hypoxia were searched in China National Knowledge Infrastructure (CNKI), Wanfang Med Online, VIP, China Biology Medicine disc and other databases, a standardized prescription database was established after screening and standardization of prescription data in the literature. The composition rules of these prescription including drug frequency, drug attributes, drug efficacy, drug combination, and core prescription were analyzed and displayed with visual charts. A total of 135 TCM prescriptions were included, and 229 flavored drugs were included. Among these prescriptions, the TCM with high frequency of use were Astragalus, Danshen, Ginseng, and Angelica, etc. Four natures of the TCM were mostly warm and calm. Five flavours of the TCM were mostly sweet, bitter, and pungent. And channel tropism of the TCM mostly entered the heart, lung, and liver meridians. The frequency combination of TCM was Astragalus-Danshen and Astragalus-Angelica. The core medicines of these prescriptions were Astragalus, Danshen, Angelica, Rhodiola, Goji, and Ginseng. TCM could alleviate symptoms such as chest tightness, chest pain, coughing and wheezing, coughing, vomiting, fatigue, and loss of appetite caused by hypoxia at high altitude. Through data mining, it is concluded that the prevention or treatment of plateau hypoxic diseases mostly utilized products can nourish blood, replenish qi and dispel stasis, and help yang and dispel qi, most of them are compatible with qi tonic drugs and blood circulation and stasis dissolving drugs, and pay attention to the combination of virtual and real, yin and yang.