Mining Methodology Research Articles

Context-Based Structure Mining Methodology for Static Object Re-Identification in Broadcast Content

Technological advancement, in addition to the pandemic, has given rise to an explosive increase in the consumption and creation of multimedia content worldwide. This has motivated people to enrich and publish their content in a way that enhances the experience of the user. In this paper, we propose a context-based structure mining pipeline that not only attempts to enrich the content, but also simultaneously splits it into shots and logical story units (LSU). Subsequently, this paper extends the structure mining pipeline to re-ID objects in broadcast videos such as SOAPs. We hypothesise the object re-ID problem of SOAP-type content to be equivalent to the identification of reoccurring contexts, since these contexts normally have a unique spatio-temporal similarity within the content structure. By implementing pre-trained models for object and place detection, the pipeline was evaluated using metrics for shot and scene detection on benchmark datasets, such as RAI. The object re-ID methodology was also evaluated on 20 randomly selected episodes from broadcast SOAP shows New Girl and Friends. We demonstrate, quantitatively, that the pipeline outperforms existing state-of-the-art methods for shot boundary detection, scene detection, and re-identification tasks.

Data-driven quality improvement approach to reducing waste in manufacturing

PurposeData-driven quality management systems, brought about by the implementation of digitisation and digital technologies, is an integral part of improving supply chain management performance. The purpose of this study is to determine a methodology to aid the implementation of digital technologies and digitisation of the supply chain to enable data-driven quality management and the reduction of waste from manufacturing processes.Design/methodology/approachMethodologies from both the quality management and data science disciplines were implemented together to test their effectiveness in digitalising a manufacturing process to improve supply chain management performance. The hybrid digitisation approach to process improvement (HyDAPI) methodology was developed using findings from the industrial use case.FindingsUpon assessment of the existing methodologies, Six Sigma and CRISP-DM were found to be the most suitable process improvement and data mining methodologies, respectively. The case study revealed gaps in the implementation of both the Six Sigma and CRISP-DM methodologies in relation to digitisation of the manufacturing process.Practical implicationsValuable practical learnings borne out of the implementation of these methodologies were used to develop the HyDAPI methodology. This methodology offers a pragmatic step by step approach for industrial practitioners to digitally transform their traditional manufacturing processes to enable data-driven quality management and improved supply chain management performance.Originality/valueThis study proposes the HyDAPI methodology that utilises key elements of the Six Sigma DMAIC and the CRISP-DM methodologies along with additions proposed by the author, to aid with the digitisation of manufacturing processes leading to data-driven quality management of operations within the supply chain.

Tree species consistent co-occurrence in seasonal tropical forests: an approach through association rules analysis

Aim of study: Aassessing the existence of consistent co-occurrence between tree species that characterize seasonal tropical forests, using the association rules analysis (ARA), that is a novel data mining methodology; and evaluate evaluating the taxonomic and functional similarities between associated species.Area of study: forty-four seasonal forest sites with permanent plots (40.2 ha of total sample) located in Southeast Brazil, from which we obtained species occurrences.Material and methods: we applied association rules analysis (ARA) to the dataset of species occurrence in sites considering the criteria of support equal to or greater than 0.63 and confidence equal to or greater than 0.8 to obtain the first set of associations rules between pairs of species. This set was then submitted to Fisher’s criteria exact p-value less than 0.05, lift equal to or greater than 1.1 and coverage equal to or greater than 0.63. We considered these criteria to be able to select non-random and consistent occurring associations.Main results: We obtained a final result of 238 rules for semideciduous forest and 11 rules for deciduous forests, composed of species characteristic of vegetation types. Co-occurrences are formed mainly by non-confamilial species, which have similar functional characteristics (potential size and wood density). There is a difference in the importance of co-occurrence between forest types, which tends to be less in deciduous forests.Research highlights: The results point to out the feasibility of applying ARA to ecological datasets as a tool for detecting ecological patterns of coexistence between species and the ecosystems functioning.Keywords: data mining; coexistence; semideciduous forests; deciduous forests; biotic interaction.

An individual-based spatio-temporal travel demand mining method and its application in improving rebalancing for free-floating bike-sharing system

After the rapid expansion in the early stage, many enterprises have closed down or withdrawn from the Free-floating bike sharing (FFBS) market, the remaining few giants are also generally at a loss at present. One main reason causing these is the serious FFBS imbalance between supply and demand. As there is no fixed docking station, the individual-based identification method such as trip-chain, which is used for identifying travel demand and behaviour in traditional station-based bike sharing (SBBS) cannot be used in FFBS. Therefore, the lack of methods to obtain in-depth demand makes it unable to achieve reasonable rebalancing. This study constructs an individual-based spatio-temporal travel demand mining methodology, which is the first disaggregate travel demand mining model that suitable for FFBS. The proposed methodology consists of three steps. A spatio-temporal trajectory clustering algorithm is first developed to obtain an individual’s frequent trajectory clusters, and then a sequential pattern mining algorithm is applied to users who have multiple spatio-temporal trajectory clusters to extract travel patterns and trajectory sequential relations in patterns. A point clustering method is used finally to identify spatial relationships among different trajectory clusters. Besides, a zone aggregating method is proposed that aggregated granularity could be flexible adjusted for zone demand imbalance analysis. Based on these, how to utilize identified frequent pattern trajectories to improve rebalancing is studied. The proposed methodology is applied to Beijing Mobike dataset, six frequent travel patterns are mined out and analyzed in detail. On this basis, imbalance and rebalancing analysis are carried out with the case study at last. Consequently, this research contributes a powerful tool to achieve accurate FFBS demand analysis and rebalancing.

Graduate Employment Prospects Post COVID Pandemic Lockdown

The unprecedented outbreak of corona virus has left a very bleak impact on the graduate job markets. With Employers themselves fighting for survival, any new manpower addition at these times especially greenhorns in any forms are unlikely or have witnessed drastic reduction. Futuristic Analysis applied in this research is an art of contemplating future by using data mining methodologies on huge current available information and systematic interpretation of probabilistic real future through data elements. Graduates generally need to find work to support themselves and contribute to economy. Currently, incertitude has made room in student graduates’ minds regarding work as what is been in educated in their institutions till the lockdown and new things they heard during lockdown and how to adjust to the new normal of work post lockdown. Hence, this paper explores what will be the nature, mode and choice of work for graduate greenhorns beginning their career path post lockdown.

Data-Driven Dispatching Rules Mining and Real-Time Decision-Making Methodology in Intelligent Manufacturing Shop Floor with Uncertainty.

In modern manufacturing industry, the methods supporting real-time decision-making are the urgent requirement to response the uncertainty and complexity in intelligent production process. In this paper, a novel closed-loop scheduling framework is proposed to achieve real-time decision making by calling the appropriate data-driven dispatching rules at each rescheduling point. This framework contains four parts: offline training, online decision-making, data base and rules base. In the offline training part, the potential and appropriate dispatching rules with managers’ expectations are explored successfully by an improved gene expression program (IGEP) from the historical production data, not just the available or predictable information of the shop floor. In the online decision-making part, the intelligent shop floor will implement the scheduling scheme which is scheduled by the appropriate dispatching rules from rules base and store the production data into the data base. This approach is evaluated in a scenario of the intelligent job shop with random jobs arrival. Numerical experiments demonstrate that the proposed method outperformed the existing well-known single and combination dispatching rules or the discovered dispatching rules via metaheuristic algorithm in term of makespan, total flow time and tardiness.

Reliability analysis of systems with discrete event data using association rules

AbstractWith the popularization of big data, an increasing number of discrete event data have been collected and recorded during system operations. These events are usually stored in the form of event logs, which contain rich information of system operations and have potential applications in fault diagnosis and failure prediction. In manufacturing processes, various levels of correlations exist among the events, which can be used to predict the occurrence of failure events. However, two challenges remain to be solved for effective reliability analysis and failure prediction: (1) how to leverage various information from the event log to predict the occurrence of failure events and (2) how to model the effects of multiple correlations on the prediction. To address these issues, this paper proposes a novel reliability model, which integrates Cox proportional hazards (PHs) regression into survival analysis and association rule mining methodology. The model is used to evaluate the probability of failure event, which occurs within a certain period of time conditional on the occurrence history of correlated events. To estimate parameters and predict occurrence of failure events in the model, an effective algorithm is proposed based on piecewise‐constant time axis division, Cox PHs model, and maximum likelihood estimation. Unlike the existing literature, our model focuses on the interactions among events. The applicability of the proposed model is illustrated through a case study of a manufacturing company. Sensitivity analysis is conducted to illustrate the effectiveness of the proposed model.

Academic Performance Prediction of Undergraduate Students using Decision Tree Algorithm

Data mining is a technique for extracting meaningful information or patterns from large amounts of data. These techniques are frequently utilised for analysis and prediction in practically all fields around the world. It's employed in a variety of fields, including education, business, health care, fraud detection, financial banking, and manufacturing engineering. This study explores the Decision Tree data mining methodology for predicting undergraduate students' academic performance.

Prediction model for the spread of the COVID-19 outbreak in the global environment

COVID-19 has long become a worldwide pandemic. It is responsible for the death of over two million people and posed an economic recession. This paper studies the spread pattern of COVID-19, aiming to establish a prediction model for this event. We harness Data Mining and Machine Learning methodologies to train regression models to predict the number of confirmed cases in a spatial-temporal space. We introduce an innovative concept ‒ the Center of Infection Mass (CoIM) ‒ adapted from the field of physics. We empirically evaluated our model on western European countries, based on the CoIM index and other features, and showed that a relatively high accurate prediction of the spread can be obtained. Our contribution is twofold: first, we introduced a prediction methodology and proved empirically that a prediction can be made even to the range of over a month; second, we showed promise in adopting the CoIM index to prediction models, when models that adopt the CoIM yield significantly better results than those that discard it. By applying our model, and better controlling the inherent tradeoff between life-saving and economy, we believe that decision-makers can take close to optimal measures. Thus, this methodology may contribute to public welfare.

Effects of the COVID-19 Pandemic on Mental Health in Peru: Psychological Distress.

This pandemic has been classified as a “psychological pandemic” that produces anxiety, depression, post-traumatic stress disorder, and sleep disorders. As the mental health effects of the Coronavirus Disease 2019 (COVID-19), caused by SARS-CoV-2, continue to unfold, there are still large knowledge gaps about the variables that predispose individuals to, or protect individuals against the disease. However, there are few publications on the effects of the COVID-19 pandemic on the mental health of citizens in Latin American countries. In this study, the effects that COVID-19 had on citizens of Peru have been described. For this, 1699 questionnaires, collected between 2 April and 2 September 2020, were analyzed. Descriptive, bivariate analysis was performed with odds ratio (OR) calculations and a data mining methodology. Sociodemographic variables (from the General Health Questionnaire), health conditions and perception, symptoms, and variables related to contact and preventive measures regarding COVID-19 were analyzed. As compared to other countries, less affectation of mental health and increased use of preventive measures were observed. It has been suggested that the country’s precarious health system and poverty rates prior to the pandemic may justify higher mortality figures in Peru than in other Latin American countries, despite prompt action for its containment and compliance with the protective measures. Psychological distress had a greater incidence in women, young people, people without a partner, and people without university studies. The most significant conditioning variables were self-perceived health status, headache or muscle pain over the past 14 days, level of studies, and age. The extensive use of preventive measures against COVID-19 is in line with the strict legislative measures taken, and this is, in turn, in line with other countries when looking at the lower effect on mental health, but contrary when focusing on the high lethality identified. The need to include the economy or availability and quality of healthcare in future studies arises, as well as the suitability to analyze the cause for differences between countries.

Cutting Resistance Laboratory Testing Methodology for Underwater Coal Mining

The bucket-wheel dredge “Kovin I” for underwater coal mining with bucket-wheel type UCW-450 has been in operation for over 20 years. Based on analyzing the bucket-wheel dredger performance, productivity, maintenance costs, and reliability, a rational decision was made: to rehabilitate the most essential parts of the dredge, including the bucket wheel and the gearbox. However, the selection and construction of the excavator parts were performed on the ground of available laboratory data for digging resistance. The data itself was determined by the testing methodology that did not include the influence of surrounding water pressure at a certain depth of mining. According to the previous findings, it was necessary to develop a specific research and testing program that would involve appropriate laboratory testing of the geomechanical parameters. These were to represent the influence of hydrostatic water pressure on the working environment—coal. Nevertheless, geomechanical laboratory research tests were initially modified to provide reliable data of cutting resistance, especially in the water under different hydrostatic pressures, fully simulating the “in situ” working conditions of mining, i.e., cutting.

Employing Google Trends and Deep Learning in Forecasting Financial Market Turbulence

In this paper we apply text mining methodologies on a set of 10,000 Central Bank speeches to construct a financial dictionary, based on which we use Google Trends indices to measure people’s interest in financial news. Particularly, we investigate the relationship between these indices and financial market turbulence leveraging on Deep Learning techniques, which are benchmarked against a variety of Machine Learning algorithms and traditional statistical techniques. Our main finding is that Google queries convey information able to predict future market turbulence in a short time period (one month), and that Deep Learning algorithms clearly outperform over benchmark techniques. Google Trends can provide useful input in the creation of crisis Early Warning Systems, as social data are more responsive compared to official financial indicators, which are usually available with a lag of several weeks or months. Thus, such an Early Warning System (EWS) that is continuously updated with current social data can be a valuable tool for policymakers, as it can immediately identify signs of whether a crisis is imminent or not.

Leveraging electronic health record data to inform hospital resource management : A systematic data mining approach.

Early identification of resource needs is instrumental in promoting efficient hospital resource management. Hospital information systems, and electronic health records (EHR) in particular, collect valuable demographic and clinical patient data from the moment patients are admitted, which can help predict expected resource needs in early stages of patient episodes. To this end, this article proposes a data mining methodology to systematically obtain predictions for relevant managerial variables by leveraging structured EHR data. Specifically, these managerial variables are: i) Diagnosis categories, ii) procedure codes, iii) diagnosis-related groups (DRGs), iv) outlier episodes and v) length of stay (LOS). The proposed methodology approaches the problem in four stages: Feature set construction, feature selection, prediction model development, and model performance evaluation. We tested this approach with an EHR dataset of 5,089 inpatient episodes and compared different classification and regression models (for categorical and continuous variables, respectively), performed temporal analysis of model performance, analyzed the impact of training set homogeneity on performance and assessed the contribution of different EHR data elements for model predictive power. Overall, our results indicate that inpatient EHR data can effectively be leveraged to inform resource management on multiple perspectives. Logistic regression (combined with minimal redundancy maximum relevance feature selection) and bagged decision trees yielded best results for predicting categorical and numerical managerial variables, respectively. Furthermore, our temporal analysis indicated that, while DRG classes are more difficult to predict, several diagnosis categories, procedure codes and LOS amongst shorter-stay patients can be predicted with higher confidence in early stages of patient stay. Lastly, value of information analysis indicated that diagnoses, medication and structured assessment forms were the most valuable EHR data elements in predicting managerial variables of interest through a data mining approach.

Investigating the school characteristics/attributes via the relationships between school management efficiency and representative factors of mobile e-learning: DEA and data mining methodology

The aim of this study is to detect the school characteristics/attributes by examining the efficiency of school management related to innovative teaching through digital mobile e-learning. This will be conducted by evaluating the results of DEA efficiency measure and data mining method (DMM).The results of DMM indicate that the schools with the total number of students in schools about 1400-3000 persons, the teacher-student ratio between 7.4 %-8.0 %, the tablet PC numbers about 1200-3000 units, the technical teacher ratio of digital mobile e-learning is about 8%-16% and the total equipment expenses associated with tablet PC about the range of 1.5-3.0 Million NTD could obtain higher operational efficiency of school management through Innovative Teaching via Digital Mobile e-learning. Based on the analytical results, the ranks of school management efficiency could divide into three groups, in the high-efficiency group (TE=1), there are three public high schools and one private higher vocational school. These all high schools are in northern Taiwan. In the medium-efficiency group (TE 0.85∼0.99), there is only one school in northern Taiwan. The low-efficiency school group (TE <0.85), there are three public schools and one private high vocational school. The three public schools are in northern Taiwan while one private high vocational school is in eastern Taiwan. In practice, we find that the public high schools are more efficient than the private high schools and public high schools are more efficient than private high schools that can achieve digital mobile e-learning. Also, and schools located in northern Taiwan more efficient than elsewhere. These research findings can also become a reference for educational institutions in developing strategies and policies for digital mobile e-learning in high school of Taiwan area.

Design space optimisation of an unmanned aerial vehicle submerged inlet through the formulation of a data-fusion-based hybrid model

ABSTRACTThe research focuses on the design space optimisation of National Advisory Committee for Aeronautics (NACA) submerged inlets through the formulation of a hybrid data fusion methodology. Submerged inlets have drawn considerable attention owing to their potential for good on-design performance, for example during cruise flight conditions. However, complexities due to the geometrical topology and interactions among various design variables remain a challenge. This research enhances the current design knowledge of submerged inlets through the utilisation of data mining and Computational Fluid Dynamics (CFD) methodologies, focusing on design space optimisation. A two-pronged approach is employed where the first step encompasses a low-fidelity model through data mining and surrogate modelling to predict and optimise the design parameters, while the second step uses the Design of Experiments (DOE) approach based on the CFD results for the candidate design geometry to construct a surrogate model with high fidelity for design refinement. The feasibility of the proposed methodology is demonstrated for the optimisation of the total pressure recovery of a NACA submerged inlet for the subsonic flight regime. The proposed methodology is found to provide good agreement between the surrogate and CFD-based model and reduce the optimisation processing time by half in comparison with conventional (global-based) CFD optimisation approaches.

Application of a Fuzzy Logic Based Methodology to Validate the Hydrochemical Characterization and Determining Seasonal Influence of a Watershed Affected by Acid Mine Drainage.

The Odiel River Basin, located in the Iberian Pyrite Belt (IPB), is heavily affected by acid mine drainage (AMD), which occurs when pyritic minerals from sulfide mining areas are exposed to atmospheric, hydrological or biological weathering. This paper presents a hydrochemical characterization of parameters in the Odiel River Basin by means of Fuzzy Logic and data mining methodologies to determine the seasonal influence of AMD in polluted waters that have not been used before for a basin in this environmental area. This technique was proven to be effective, providing results that could not be achieved by using classic statistics, because it allows us to characterize the different parameters separately and also their relationships in waters affected by AMD in a qualitative manner based on the antecedents and according to the conditions (rules) imposed by the consequents (in this case, the Fe(II) and accumulated rainfall over 30 days). Thus, it was possible to confirm that hydrochemistry is greatly affected by seasonal changes, with a higher pH in the wet season (up to 8.59) compared to 2.12, the minimum pH value reached in the dry season. Accordingly, higher concentrations of most of the metals were observed in the dry season (e.g., up to 4000 mg/L of Fe (II)), with the exception of the values found after the first rains that occur in the early fall. With the use of the Fuzzy Logic technique, it was observed that, during the wet season, lixiviates with a higher Fe content have higher metal concentrations, and in the dry season, the behavior is the opposite.

Mining Frequent Itemsets Without Candidate Generation In Machine Learning

Mining of regular trends in group action databases, time series databases, and lots of different database types was popularly studied in data processing research. Most previous studies follow the generation-and-test method of associate degree Apriori-like candidate collection. In this study, we seem to propose a particular frequency tree like structure, which is associated degree of prefix-tree like structure that is extended to be used for compressed storage, crucial knowledge of the frequency pattern, associated degrees create an economic FP-tree mining methodology, FP growth, by the growth of pattern fragments for the mining of the entire set of frequent patterns. Three different mining techniques are used to outsize the information which is compressed into small structures such as FP-tree that avoids repetitive information scans, cost. The proposed FP-tree-based mining receives an example philosophy of section creation to stay away from the exorbitant age of several competitor sets, and an apportioning-based, separating and-overcoming technique is used to divide the mining task into a contingent knowledge base for restricted mining designs that effectively reduces the investigation field.

Excavating Archaeological Texts: Applying Digital Humanities to the Study of Archaeological Thought and Banal Nationalism

ABSTRACT To date, the evolution of archaeological knowledge production and theory has been discussed and analyzed using qualitative methods by reading vast amounts of archaeological texts in search of specific discourses or framings of the past. In this paper, we present text mining methodologies from digital humanities that can be applied to large corpora of archaeological texts to trace and evaluate changing knowledge practices. Such a big data approach is imperative. Due to the rapid increase of archaeological publications, qualitative research into the intellectual history of archaeology has become complicated and highly selective. The big data methods presented in this study were tested on a large corpus (4,811 texts totaling over 51 million words) of different types of archaeological texts from the Dutch-speaking part of Belgium. The different text mining tools were successful in identifying theoretical trends. Our tools were also successful in charting the decrease in quality due to changed organizational circumstances (developer-led archaeology). Furthermore, we could also map changing banal nationalist framings of the past.

Information, Communications and Media Technologies for Sustainability: Constructing Data-Driven Policy Narratives

This paper introduces the idea of data-driven narratives to examine how the use of information, communications, and media technologies (ICMTs) impacts the sustainable growth of economies. While ICMTs have regularly been advocated as a policy tool for growth and development, there is a research gap in empirical studies validating how such policies may be effective. This analysis is based on historical panel data from 39 economies across the developed North (19) and developing South (20). The industry-standard Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology was applied to construct narratives that weave extant theories with empirical data. The art of developing data-driven narratives is rarely addressed in previous research articles. In the narrative approach, prior research on how ICMTs and sustainable growth are quantitatively scored and measured is reviewed. Panel data from authoritative sources such as the United Nations, World Economic Forum, and Sustainable Society Index were collected, cleansed, and conglomerated for data analytics. This was followed by evidence-based reasoning to examine any possible relationships between ICMT development and the sustainable growth of economies across the “North” and “South”. The findings reveal that there are differentiated outcomes in sustainable growth in high- and low-income economies. This poses legitimate questions as to whether low-income economies will be able to meet the UN’s Sustainable Development Goals by 2030 through the intermediation of ICMTs. It is the intended contribution of this paper to exemplify how data-driven narratives using CRISP may construct rich stories about ICMT for sustainability for the purposes of sharing good practice as well as lessons learned.

Data Mining preparation: Process, Techniques and Major Issues in Data Analysis

Data preparation is an essential stage in data analysis. Many institutions or companies are interested in converting data into pure forms that can be used for scientific and profit purposes. It helps you set goals regarding system capabilities and features or the benefits your company expects from its investment. This purpose creates an immediate need to review and prepare the data to clean the raw data. In this paper, we highlight the importance of data preparation in data analysis and data extraction techniques, in addition to an integrated overview of relevant recent studies dealing with mining methodology, data types diversity, user interaction, and data mining. Finally, we suggest some potential suggestions for future research and development.