Proper Data Mining Research Articles

Data Mining for the Global Multiplex Weekly Average Income Analysis

The box office (BO) income had significantly declined up to 80% in 2020, as the COVID-19 pandemic emerged. To minimize further financial risks, multiplex (multiple cinema complexes) owners need to analyze their potential income for each movie, each week. Therefore, we developed a proper data mining strategy that allows multiplex owners to analyze and discover insights on how successfully produced movies could be. The methodology comprises (1) data loading and exploration, (2) data cleaning, (3) data selection, integration, and transformation using Pentaho, (4) data mining in which the results were stored in the MySQL database, and (5) pattern evaluation and presentation using Qlik Sense as the Business Intelligence (BI) dashboard. Based on our data mining methodology, we revealed that drama, comedy, action, and thriller are favorite genres. We also found that DreamWorks Animation and Pixar Animation Studios are both the most popular production houses, even Apatow Productions and Escape Artists still have the biggest revenue on average.

Metamodel-Interpreted Data Mining for Stability and Efficiency Enhancement of Multistage Axial-Flow Compressors

Abstract The tradeoff between higher efficiency and wider stability of performance map is still one of the bottlenecks to hamper the further research and development of advanced multistage axial-flow compressor. The recent rapid growth of computational resources and artificial intelligence has enabled data mining as one of the most effective and potential ways to gain a deep insight into the complex correlations between aerodynamic performance and three-dimensional geometry parameters. In the open literatures, however, few research works have been found on using the data mining that is independent of design optimization to extract priori design guidelines for multistage axial-flow compressor mainly due to the lack of proper data mining method focused on the interpretation of metamodel with full use of limited time-consuming computational fluid dynamics dataset. To tackle this issue, a metamodel-interpreted data mining framework is developed in which extreme gradient boosting (XGBoost) metamodel combined with Shapley additive explanation (SHAP) model are employed to locally interpret the feature importance of each sample in the computational fluid dynamics dataset and then extract the design guidelines in terms of the most influential geometry parameters and their beneficial variation directions. The developed method is applied to data mining of design guidelines for efficiency and stability enhancement of a front 3.5-stage transonic axial-flow compressor in ship-board gas turbine usage. The results show that the aerodynamic performance of the investigated multistage compressor is most sensitive to three-dimensional geometry parameters related to blade lean, blade twist, and variable stators. Specially, the variable stators mainly affect the stall margin at part speed. The blade lean mainly influences the adiabatic efficiency at design speed as well as the stall margin at both speeds, while the blade twist mainly influences the aerodynamic performance at design speed. New designs followed by the design guidelines are obtained and critical performance indicators related to the goals of the data mining task are verified. The stall margin at part speed is widened to 5.87% with adjustment of blade lean and twist and further to 23.31% with additional adjustment of variable stators. The peak adiabatic efficiency at design speed is improved by 0.06% in spite of extremely limited potential for efficiency enhancement of the original design. The present work is of scientific significance as well as industrial application value in the three-dimensional design optimization of advanced multistage axial-flow compressor at the affordable computational cost.

The New Method for Analyzing Technology Trends of Smart Energy Asset Performance Management

The development of emerging technologies not only has recently affected current industrial production but also has generated promising manufacturing opportunities that impact significantly on social and economic factors. Exploring upcoming renovation tendencies of technologies prematurely is essential for governments, research and development institutes, and industrial companies in managing strategies to achieve dominant advantages in business competitiveness. Additionally, the prospective changes, the scientific research directions, and the focus of technologies are crucial factors in predicting promising technologies. On the other hand, Industry 4.0 revolutionizes standards and models by accompanying significant technology developments in numerous sectors, including the sector of Smart energy. Moreover, asset performance management is always a prominent topic that has attained prevalence over the last decade because numerous challenges force all industrial companies to optimize their asset usability. However, to the best of our knowledge, no study reported an analysis of technology trends of asset performance management in the Smart energy sector by using proper data mining methods. Hence, this paper aims to fill in this gap and provide an analysis of technology trends of asset performance management in the Smart energy sector by structuring and exploring research subjects, considering problems, and solving methods with numerous experiments on scientific papers and patent data.

EXPLAINABILITY OF NEURAL NETWORK CLUSTERING IN INTERPRETING THE COVID-19 EMERGENCY DATA

Among other hospitalization causes and cases, the clinical emergency is a critical case and the data of the reporting patients are biased as well as poorly managed due to the chaotic situation. The world has faced chaos over the past year due to the frequent waves of COVID-19 and the resulting emergencies. The data banks, linked with the clinical emergencies require serious quantitative and qualitative analysis to drive interpretable conclusions for necessary future emergency measures and to develop explainable artificial intelligence tools. This important procedure involves the clear understanding of the data patterns and topologies, which is a great challenge for the multidimensional data sets. Mathematically, the topological mapping can resolve this problem by mapping higher-dimensional data to two-dimensional representation, based on the overall association. Proper data mining and pattern recognition can help in improving the rapid patients admission, in providing the medical resources timely and in proper patient administration. In this paper, the importance of self-organizing maps, to interpret the hospital data, particularly for the COVID-19 epidemic is discussed in detail. Important variables are identified with the aid of networks and mappings.

Affective-Blue Design Methodology for Product Design Based on Integral Kansei Engineering

Sustainable product designs always draw much attention. However, sustainable or green products are usually costly. This contradiction can be solved via blue design. The concept of blue design originates from the blue economy which is a popular strategy for providing sustainable, healthy, but cheap socioeconomic activities. This study innovatively implements the ideas of sustainability and economy from the blue economy, and the affection (or Kansei in Japanese) from the Kansei engineering into a product design process to become a novel affective-blue design methodology of a product form. The proposed methodology mainly contains three aspects. The first aspect is the merge of a novel Kansei blue model with the traditional Kansei engineering to deal with the semantic space and form decomposition issues encountered in the product form designing process. The second aspect is the adoption of proper data mining schemes to optimally trim and obtain the kernel information from the Kansei evaluation data of products. The third aspect is the usage of appropriate machine learning schemes to establish a precise relationship between product images and design elements from the kernel information. A case study was conducted for the form design of a computer-numerical-control lathe to evaluate the effectiveness of our proposed methodology. The verification results, that all predictive errors are within 4.5% for test samples, show that our blue-affective design methodology is quite satisfying. Through applying this proposed methodology, designers may correctly evaluate and easily catch the essential blue and affective design factors for designing a good industrial product, such as a computer-numerical-control machine tool.

Building categorization revisited: A clustering-based approach to using smart meter data for building energy benchmarking

Current building energy benchmarking systems categorize buildings into peer groups by static characteristics such as climate zones and building types, which cannot account for the huge variation in building operations. Grouping buildings with diverse operations for benchmarking could result in misleading results. The smart meters provide an opportunity to feature the dynamic characteristics of building operations, but proper data mining techniques are needed to use the data for benchmarking. Accordingly, this paper proposes a framework that makes use of the time-series energy consumption data to categorize buildings by their operations and conduct energy benchmarking within each category. The proposed framework is based on 3-step K-means clustering and consists of two main parts: (1) Operation quantification, and (2) Building categorization and benchmarking. The framework was tested on a dataset of 81 buildings in Singapore. Two baseline methods were also implemented for comparison. The results show that the proposed framework successfully categorized the buildings by their operational similarities and made a significant impact on the energy benchmarking results. Further, the superiority of operation-based energy benchmarking is manifested by investigating two typical buildings where the proposed framework disagreed with the baselines. It is necessary to integrate building operations in energy benchmarking so that the energy performance is evaluated more precisely and higher energy saving potential can be uncovered.

A comparative study of clustering techniques for electrical load pattern segmentation

Smart meters have been widely deployed in power networks since the last decade. This trend has resulted in an enormous volume of data being collected from the electricity customers. To gain benefits for various stakeholders in power systems, proper data mining techniques, such as clustering, need to be employed to extract the underlying patterns from energy consumptions. In this paper, a comparative study of different techniques for load pattern clustering is carried out. Different parameters of the methods that affect the clustering results are evaluated and the clustering algorithms are compared for two data sets. In addition, the two suitable and commonly used data size reduction techniques and feature definition/extraction methods for load pattern clustering are analysed. Furthermore, the existing studies on clustering of electricity customers are reviewed and the main results are highlighted. Finally, the future trends and major applications of clustering consumption patterns are outlined to inform industry practitioners and academic researchers to optimize smart meter operational use and effectiveness.

Heavy Rainfall Prediction using Gini Index in Decision Tree

In existing systems, it happens that sometimes the data is not accurate and proper data mining techniques not being used and this increases the complexity.We as humans are bound to make mistakes while predicting weather conditions which might result in damage to both life and property. To avoid this, we use data mining algorithms for early warning of climatic conditions such as like maximum temperature, minimum temperature wind speed, rainfall, humidity, pressure, dew point, cloud, sunshine and wind direction from data to predict rainfall. But by using proper algorithms for datasets and using the right metrics, we can achieve the accurate results in prediction of rainfall. Hence, we apply the Decision tree algorithm using Gini Index in order to predict the precipitation with accuracy and it is completely based on the historical data.

Dynamic characteristic of the forth road bridge estimated with GeoSHM

The importance of bridge health monitoring and management has been recognized by authorities of long-span bridges throughout the world in recent years. The GeoSHM consortium, led by the University of Nottingham, was awarded a Feasibility Study (FS) grant in 2013 by the European Space Agency (ESA) to investigate how to use integrated GNSS and Earth Observation technologies for the structural health monitoring of large bridges. During the GeoSHM FS period a small monitoring system was installed on the Forth Road Bridge in Scotland and the consortium have gathered huge data sets and rich experience regarding the design and implementation of GeoSHM according to essential user needs. This paper, based on the data from GNSS receivers installed on the two middle span sites and top of the southern tower of the Forth Road Bridge, intends to reveal the dynamic characteristics of the bridge. By using a moving average filter, Fast Fourier Transformation (FFT) and the peak-picking approach, the three-dimensional (3D) displacement time series under ambient excitation were decomposed into long-period movement and dynamic vibration response. The results demonstrate that the movement of the Forth Road Bridge in lateral direction is mainly caused by wind loading, and the correlation is about 0.7. In vertical direction, the displacements of middle span sites under the normal traffic loadings can reach 0.3 m and because of the main cable linking the middle span and top of the tower, the longitudinal movement of the southern tower top site has a high correlation with the vertical displacements of middle span sites. It has been found that due to the stiffness of the tower the trend terms inside lateral and vertical time series mainly consist of multipath effect and quasi-static displacement. The dynamic vibration frequencies and corresponding motion amplitudes were also extracted. It is found that the first natural frequencies of the middle span of the Forth Road Bridge are 0.065 Hz, 0.15 Hz and 0.104 Hz for lateral, longitudinal and vertical directions, respectively. For the south tower, vibration frequencies of 0.18 Hz can be seen in all three directions, but 0.104 Hz is only visible in longitudinal component because of the cables linking the tower and middle span. It demonstrates that with a proper data mining approach both the low frequency responses and dynamic vibration characteristics of a large bridge under ambient loadings can be extracted from GNSS data sets. Thus, GeoSHM can be used by bridge owners as an effective tool to assess the operational conditions of the bridge.

Reconciling evidence-based medicine and precision medicine in the era of big data: challenges and opportunities.

This era of groundbreaking scientific developments in high-resolution, high-throughput technologies is allowing the cost-effective collection and analysis of huge, disparate datasets on individual health. Proper data mining and translation of the vast datasets into clinically actionable knowledge will require the application of clinical bioinformatics. These developments have triggered multiple national initiatives in precision medicine—a data-driven approach centering on the individual. However, clinical implementation of precision medicine poses numerous challenges. Foremost, precision medicine needs to be contrasted with the powerful and widely used practice of evidence-based medicine, which is informed by meta-analyses or group-centered studies from which mean recommendations are derived. This “one size fits all” approach can provide inadequate solutions for outliers. Such outliers, which are far from an oddity as all of us fall into this category for some traits, can be better managed using precision medicine. Here, we argue that it is necessary and possible to bridge between precision medicine and evidence-based medicine. This will require worldwide and responsible data sharing, as well as regularly updated training programs. We also discuss the challenges and opportunities for achieving clinical utility in precision medicine. We project that, through collection, analyses and sharing of standardized medically relevant data globally, evidence-based precision medicine will shift progressively from therapy to prevention, thus leading eventually to improved, clinician-to-patient communication, citizen-centered healthcare and sustained well-being.

Investigating the use of business, competitive and marketing intelligence as management tools in the mining industry

The main objective of this research study is to investigate the extent to which business intelligence, competitive intelligence and marketing intelligence are used within the mining industry. Business intelligence, competitive intelligence and marketing intelligence are the management tools used to mine information to produce up-to-date intelligence and knowledge for operative and strategic decision making. A structured questionnaire is used for the study. A total of 300 mines are randomly selected from a research population of mining organizations in South Africa, Africa and globally. The respondents are all part of senior management. A response rate of 64% is achieved. The results indicat that more than half of the respondents do not have real-time intelligence and proper data mining tools to identify patterns and relationships within a data warehouse. Although a large proportion agrees that their organizations have systematic ways of gathering these different types of intelligence and use them for strategic decision making, there is a significant proportion that did not have any systems. Statistically and practically significant positive relationships with a large effect are found among the dimensions of business intelligence, marketing intelligence, competitive intelligence and perceived business performance

Fault diagnosis of rolling element bearing with intrinsic mode function of acoustic emission data using APF-KNN

This paper presents a fault diagnosis technique based on acoustic emission (AE) analysis with the Hilbert–Huang Transform (HHT) and data mining tool. HHT analyzes the AE signal using intrinsic mode functions (IMFs), which are extracted using the process of Empirical Mode Decomposition (EMD). Instead of time domain approach with Hilbert transform, FFT of IMFs from HHT process are utilized to represent the time frequency domain approach for efficient signal response from rolling element bearing. Further, extracted statistical and acoustic features are used to select proper data mining based fault classifier with or without filter. K-nearest neighbor algorithm is observed to be more efficient classifier with default setting parameters in WEKA. APF-KNN approach, which is based on asymmetric proximity function with optimize feature selection shows better classification accuracy is used. Experimental evaluation for time frequency approach is presented for five bearing conditions such as healthy bearing, bearing with outer race, inner race, ball and combined defect. The experimental results show that the proposed method can increase reliability for the faults diagnosis of ball bearing.

Benefits and Barriers in Mining the Healthcare Industry Data

The authors’ paper addresses the applications of data mining within the healthcare industry. Healthcare data are seen as one of the more rewarding and most difficult of all data to analyze. Proper data mining techniques provide the methodology and technology to transform the voluminous amounts of data into useful information for decision making. Data mining can be utilized to help find cures for existing diseases, uncovering patterns for genetic diseases and the causes of new diseases across the globe. By implementing data mining techniques the industry is finally gaining control over the inadequacy of readily available records. Data mining has been used in patient care, healthcare plans, and administration. By utilizing these methods, hospitals and healthcare insurance providers alike are able to save millions of dollars, administration headaches, and most importantly, countless lives.