Mining Approach Research Articles

Integration of Price Data in Wind Power Sales Systems Using Association Rule Mining Combined with Deep Learning Algorithms

With the growing attention of the global population towards renewable energy sources such as wind power derived from natural resources such as Solar, Geothermal, and Wind energy, there is a growing need for genuine estimation of wind energy. Wind energy is important in the supply of electricity in the global energy markets because of its enormous importance in the delivery of renewable energy. As such, it is crucial for accurate appreciation of the power of the wind to ably respond to issues that relate to the trading of power while at the same time addressing issues to do with planning, scheduling and strategic positioning of wind power generation. Therefore, the present work aims to develop a new model known as the Association Rule with DL-based Wind Power Generation and Price Prediction (ARDL-WPGPP). It utilizes two datasets: An Energy dataset includes various columns like tie, wind onshore forecast, and price actual, whereas the weather features dataset includes only wind speed. These datasets are combined to create a dataset where each transaction represents 2 hours of wind generation. A data mining approach is employed to uncover hidden patterns, rules, concepts, and correlations within these datasets, operating on various types of data including quantitative, textual, and multimedia formats. To efficiently extract rules from the dataset, an improved Apriori algorithm is introduced. Subsequently, the generated rules incorporating wind speed are passed into an improved LSTM model, which learns by comparing the label data. The price actual value serves as the label data, assigning labels to data points based on their actual price value. High price actual values indicate high wind power prices, while low values indicate low wind power prices.

Unveiling the causes of waiting time in business processes from event logs

Waiting times in a business process often arise when a case transitions from one activity to another. Accordingly, analyzing the causes of waiting times in activity transitions can help analysts identify opportunities for reducing the cycle time of a process. This paper proposes a process mining approach to decompose observed waiting times in each activity transition into multiple direct causes and to analyze the impact of each identified cause on the process cycle time efficiency. The approach is implemented as a software tool called Kronos that process analysts can use to upload event logs and obtain analysis results of waiting time causes. The proposed approach was empirically evaluated using synthetic event logs to verify its ability to discover different direct causes of waiting times. The applicability of the approach is demonstrated in a real-life process. Interviews with process mining experts confirm that Kronos is useful and easy to use for identifying improvement opportunities related to waiting times.

Paying Back to Good Deeds: A Text Mining Approach to Explore Don-jjul as Pro-consumption Behavior

Paying Back to Good Deeds: A Text Mining Approach to Explore Don-jjul as Pro-consumption Behavior

Natural language processing applications in social network analysis: a data mining approach

Natural language processing applications in social network analysis: a data mining approach

A Panoramic View on International Higher Education Studies from a Global Perspective

With globalization, international education has become much more accessible to more people around the world. International higher education (IHE) has been among the most studied topics in higher education in recent years. In this context, the present study aims to investigate the studies conducted on IHE through a systematic literature review by analyzing studies published between 1965 and 2021 and employs social network analysis (SNA) and text-mining techniques. All these findings show that global, national, and institutional strategies are effective in the increase of interest in international education and especially in the increase of research. In this connection, this study provides an overview of trends; academic production in IHE has been researched with the data mining and analytics approaches, bibliometric method and the analysis of social networks. Thus, a better understanding and interpretation of the leading themes in the literature of internationalization in higher education is possible to achieve a better understanding of the field of intellectual scientific knowledge in the literature on globalization and IHE.

Strategy of geothermal energy development as a renewable energy source in West Java Indonesia

Background: Indonesia has vast renewable energy potential, including biofuels, biomass, and bioenergy from tropical biodiversity spread across the country. Hydropower and geothermal energy are the only forms of renewable energy used to generate electricity and are connected to the grid. Geothermal energy may be incorporated into the grid to create hybrid energy systems that will help to reduce the high energy demand while maintaining low energy costs and net present costs. There are now 14 biosphere reserves in Indonesia, divided into 24 units of core zones, six units of buffer zones, and 13 units of transition zones. The West Java Province has a geothermal potential of 6,101 MWe or 21% of Indonesia's total geothermal resources. Currently, the installed capacity of electricity from geothermal energy in West Java is 1075 MWe or 89% of the total national installed capacity of 1196 MWe. Method: This paper reviews West Java Province data collection from official government bureaus, state-owned businesses, and non-governmental organizations (NGO) reports on geothermal energy capacity, electricity installation, and used area of ​​geothermal power plant and will be limited to the years 2010 through 2020. The collected data will then be refined, extrapolated, and analyzed by the connected trend to aid in studying West Java geothermal growth and use SWOT method analysis. Finding: The result of this research is a strategy for optimizing the development of geothermal energy utilization. The strategies that can be developed are infrastructure improvement as an investment facilitation strategy, a strategy to leverage a costly investment and capital investment, underground mining in conservation forest areas to avoid degradation improvement and supervision of related institutions and stakeholders, implementation of environmentally sustainable development, and socializing programs and providing job opportunities for the local community. Conclusion: Indonesia has an enormous potential for renewable energy, especially geothermal, with West Java Province having the largest installed capacity. This study suggests strategies to optimize geothermal energy development, including improving infrastructure, investment facilities, underground mining, improving supervision, and sustainable development. Novelty/Originality of this study: Research on geothermal energy in West Java provides a comprehensive analysis and specific strategies to optimize the development of this energy in the area, including innovative underground mining approaches.

Sliding and Adaptive Windows to Improve Change Mining in Process Variability

A configurable process Change Mining approach can detect changes from a collection of event logs and provide details on the unexpected behavior of all process variants of a configurable process. The strength of Change Mining lies in its ability to serve both conformance checking and enhancement purposes; users can simultaneously detect changes and ensure process conformance using a single, integrated framework. In prior research, a configurable process Change Mining algorithm has been introduced. Combined with our proposed preprocessing and change log generation methods, this algorithm forms a complete framework for detecting and recording changes in a collection of event logs. Testing the framework on synthetic data revealed limitations in detecting changes in different types of variable fragments. Consequently, it is recommended that the preprocessing approach be enhanced by applying a filtering algorithm based on sliding and adaptive windows. Our improved approach has been tested on various types of variable fragments to demonstrate its efficacy in enhancing Change Mining performance.

Identification of clusters of secondary metabolite biosynthetic genes in the Camelina sativa genome

Multidrug-resistant pathogens pose an earnest risk to human health. Therefore, new antibiotics need to be developed quickly. Most of the antibiotics we use today are derived from secondary metabolites, which are produced by plants. Genome mining tools allow us to detect biosynthetic gene clusters (BGCs) responsible for the production of secondary metabolites. Focusing on the most promising BGCs-coding antibiotics with unique pathways is currently a challenge. In silico approach like genome mining are used to visualise the action of these bioactive chemicals. Camelina sativa is a well-known medicinal plant and it would be interesting to study its secondary metabolites. In this work, we found seven bioactive compounds in this plant using the genome mining approach. Further, the clusters of genes involved in the biosynthesis of these compounds were analysed with their metabolic pathways. This work illuminates new ground on the evolution of BGCs for the nutritional improvement of C. sativa.

Developing an intelligent and sustainable model to improve E-learning satisfaction based on the learner’s personality type: data mining approach in high education systems

PurposeAlthough E-learning has been in use for over two decades, running parallel to traditional learning systems, it has gained increased attention due to its vital role in universities in the wake of the COVID-19 pandemic. The primary challenge within E-learning pertains to the maintenance of sustainable effectiveness and the assurance of stakeholders' satisfaction. This research focuses on an intelligence-driven solution to recommend the most effective approach to education policymakers by considering the unique characteristics of all components within the educational system (course type, student and teacher characteristics, and technological features) to achieve a sustainable E-learning system.Design/methodology/approachThrough a systematic literature review and qualitative content analysis, a conceptual model of the critical components influencing E-learning quality and satisfaction has been developed. The proposed model comprises six main dimensions: usage, service quality, learning system quality, content quality, perceived usefulness, and individual characteristics. These dimensions are further divided into 15 components and 114 sub-components. A data mining process encompassing two scenarios has been designed to prioritize the components impacting E-learning success.FindingsIn the first scenario, data mining techniques identified the most influential components based on the features outlined in the conceptual model. According to the results, the components affecting E-learning quality enhancement in the studied case are “usage purpose, system loyalty, technical and supportive system quality, and student characteristics.” The second scenario examines the impact of individuals' personality types and learning styles on E-learning satisfaction across various aspects (Average System Satisfaction, Overall System Satisfaction, Efficiency and Effectiveness, Skill Enhancement, and Personal Enhancement). The findings reveal that, with an accuracy of over 70%, E-learning satisfaction for diplomat and guard learners is influenced by the alignment between “course learning style” and “student-suggested course learning style.” Conversely, for analyzer and researcher types, satisfaction levels are impacted by the “learning style compatible with their personality type.”Originality/valueImplementing a dynamic model founded on data mining enables educational institutions to personalize the E-learning experience for each individual as much as possible. The study’s findings indicate that “achieving higher satisfaction levels in the E-learning process is not necessarily contingent upon providing a learning style congruent with learners' personality types.” Rather, perceived and suggested learning styles exert a more profound influence. Consequently, providing prescriptive principles for higher education institutions seeking to enhance E-learning quality is inadvisable. Instead, adopting a dynamic, knowledge-based process that furnishes recommendations to policymakers for each course—tailored to the specific course type, teaching records, current processes and technology, and student type—is highly recommended.

On being green in the social media interactivity’s information seeking-sharing: Case of Generation Z in Indonesia

Social media interactivity creates consumer’s space of information seeking-sharing where its intensity could produce knowledge, creates new values and changes behavior. The aim of this study is to exploratory investigate the dual role of Generation Z’s information seeking-sharing behavior within green context through the interactive space of social media as a resource for the development of social media marketing strategy. The research employs mixed-method approach of qualitative-explorative data mining, quantitative cross-tabulation Chi-Square test, and integration. Two findings of this research are elaborated. First, consumer’s space of information-seeking leads to the process of green awareness rationalization, i.e., how environment-oriented actions can be rationalized. Second, consumer’s space of information-sharing leads to green social values, i.e., How environment-oriented actions can be socially recognized. The marketing implications of these two findings are business’ efforts to develop green-oriented strategic mindset through space of social media marketing “customer engagement” where the dual role of information seeking-sharing within green context is facilitated.

Efficient and multiplex gene upregulation in plants through CRISPR-Cas-mediated knockin of enhancers

Gene upregulation through genome editing is important for plant research and breeding. Targeted insertion of short transcriptional enhancers (STEs) into gene promoters may offer a universal solution akin to transgene-mediated overexpression while avoiding the drawbacks associated with transgenesis. Here, we introduce an “in locus activation” technique in rice that leverages well-characterized STEs for refined, heritable, and multiplexed gene upregulation. To address the scarcity of potent enhancers, we developed a large-scale mining approach and discovered a suite of STEs that are capable of enhancing gene expression in rice protoplasts. The in locus integration of these STEs into eight rice genes resulted in substantial transcriptional upregulation in the edited plants, with up to 869.1-fold increases in their transcript levels. Employing a variety of STEs, we achieved delicate control of gene expression, enabling the fine-tuning of key phenotypic traits such as plant height. Our approach also enabled efficient multiplexed gene upregulation, with up to four genes activated simultaneously, significantly enhancing the nicotinamide mononucleotide metabolic pathway. Importantly, heritability studies from the T0 to T3 generations confirmed the stable and heritable nature of STE-driven gene activation. Collectively, our work demonstrates that coupled with STE mining, leveraging genome editing for in locus activation and gene upregulation holds great promise to be widely adopted in fundamental plant research and crop breeding.

A text-mining analysis of Latin America Universities’ mission statements from a ‘Third Mission’ perspective

ABSTRACT University Mission Statements (UMS) were born by imitating a common practice in the business world, where private organisations state their core values and main purposes. Recently, there has been growing interest in analysing UMS through the lens of the Third Mission (TM) of universities. Despite the increasing attention to UMS analysis of TM at the national level, there remains a dearth of research that conducts international comparisons of UMS across various countries utilizing a TM perspective. In this study, we adopt a text mining approach commonly employed in Natural Language Processing studies to categorize 1304 UMS from 19 Latin American countries based on generalized social and economic orientations of TM. By eschewing classifications reliant on specific TM aspects and activities, our analysis aims to facilitate meaningful regional and cross-country comparisons. On average, the orientation of UMS from Latin American countries is 82% social and 55% economic, significant variations observed across countries reflecting the particularities of each Higher Education System. Our results are comparable to previous research analysing single-country UMS, utilizing interpretive content analysis and a Third Mission lens. This evidence offers a quantitative perspective that aligns with existing regional narratives, enriching our understanding of the Third Mission across Latin America.

Using Machine Learning to Explore the Impact of Borderline Hyponatremia on Adverse Outcomes in Heart Failure Patients: A Data Mining Approach

Using Machine Learning to Explore the Impact of Borderline Hyponatremia on Adverse Outcomes in Heart Failure Patients: A Data Mining Approach

Sustainable aquaculture over the last 30 years: An analysis of the scientific literature by the Text Mining approach

AbstractA literature search approach (using Scopus®, Elsevier© database) was established to identify peer‐reviewed articles published in English between 1960 and 2023 dealing with ‘sustainable aquaculture’ and focusing on specific aquaculture practices (aquaponics, integrated multi‐trophic aquaculture, biofloc and recirculating aquaculture systems). Text Mining combined with Topic Analysis was utilized to extract information from the text data of the papers identified. After an appropriate screening procedure, 1111 articles were selected. The analysis showed a gradual increase in sustainable aquaculture publications over time, peaking at more than 200 publications in 2023. The first articles on biofloc, integrated multi‐trophic aquaculture and recirculating aquaculture systems as alternative aquaculture practices began to appear in 2010, while studies in aquaponics have only been published since 2015. Most publications (40%) came from Asia, in line with the leadership of this continent in aquaculture. European also showed considerable interest in sustainable aquaculture practices, with Italy (leader in publications), Portugal and Germany researchers contributing with 111 papers on the subject in the past 30 years. This study identified the main research topics on the subject and observed how these have evolved. The papers analysed dealt mainly with optimization of aquatic life, genetic in aquaculture and disease management. The topic of protein replacement in feed was also important, with the term ‘diet’ the most frequently utilized in papers. The subjects identified could serve as valuable primary data source, offering opportunities for deeper examination, such as systematic reviews on research topics or geographic regions.

A cross-omics data analysis strategy for metabolite-microbe pair identification.

Given the pivotal roles of metabolomics and microbiomics, numerous data mining approaches aim to uncover their intricate connections. However, the complex many-to-many associations between metabolome-microbiome profiles yield numerous statistically significant but biologically unvalidated candidates. To address these challenges, we introduce BiOFI, a strategic framework for identifying metabolome-microbiome correlation pairs (Bi-Omics). BiOFI employs a comprehensive scoring system, incorporating intergroup differences, effects on feature correlation networks, and organism abundance. Meanwhile, it establishes a built-in database of metabolite-microbe-KEGG functional pathway linking relationships. Furthermore, BiOFI can rank related feature pairs by combining importance scores and correlation strength. Validation on a dataset of cesarean-section infants confirms the strategy's validity and interpretability. The BiOFI R package is freely accessible at https://github.com/chentianlu/BiOFI.

A strategy to detect metabolic changes induced by exposure to chemicals from large sets of condition-specific metabolic models computed with enumeration techniques

BackgroundThe growing abundance of in vitro omics data, coupled with the necessity to reduce animal testing in the safety assessment of chemical compounds and even eliminate it in the evaluation of cosmetics, highlights the need for adequate computational methodologies. Data from omics technologies allow the exploration of a wide range of biological processes, therefore providing a better understanding of mechanisms of action (MoA) related to chemical exposure in biological systems. However, the analysis of these large datasets remains difficult due to the complexity of modulations spanning multiple biological processes.ResultsTo address this, we propose a strategy to reduce information overload by computing, based on transcriptomics data, a comprehensive metabolic sub-network reflecting the metabolic impact of a chemical. The proposed strategy integrates transcriptomic data to a genome scale metabolic network through enumeration of condition-specific metabolic models hence translating transcriptomics data into reaction activity probabilities. Based on these results, a graph algorithm is applied to retrieve user readable sub-networks reflecting the possible metabolic MoA (mMoA) of chemicals. This strategy has been implemented as a three-step workflow. The first step consists in building cell condition-specific models reflecting the metabolic impact of each exposure condition while taking into account the diversity of possible optimal solutions with a partial enumeration algorithm. In a second step, we address the challenge of analyzing thousands of enumerated condition-specific networks by computing differentially activated reactions (DARs) between the two sets of enumerated possible condition-specific models. Finally, in the third step, DARs are grouped into clusters of functionally interconnected metabolic reactions, representing possible mMoA, using the distance-based clustering and subnetwork extraction method. The first part of the workflow was exemplified on eight molecules selected for their known human hepatotoxic outcomes associated with specific MoAs well described in the literature and for which we retrieved primary human hepatocytes transcriptomic data in Open TG-GATEs. Then, we further applied this strategy to more precisely model and visualize associated mMoA for two of these eight molecules (amiodarone and valproic acid). The approach proved to go beyond gene-based analysis by identifying mMoA when few genes are significantly differentially expressed (2 differentially expressed genes (DEGs) for amiodarone), bringing additional information from the network topology, or when very large number of genes were differentially expressed (5709 DEGs for valproic acid). In both cases, the results of our strategy well fitted evidence from the literature regarding known MoA. Beyond these confirmations, the workflow highlighted potential other unexplored mMoA.ConclusionThe proposed strategy allows toxicology experts to decipher which part of cellular metabolism is expected to be affected by the exposition to a given chemical. The approach originality resides in the combination of different metabolic modelling approaches (constraint based and graph modelling). The application to two model molecules shows the strong potential of the approach for interpretation and visual mining of complex omics in vitro data. The presented strategy is freely available as a python module (https://pypi.org/project/manamodeller/) and jupyter notebooks (https://github.com/LouisonF/MANA).

Standardising job descriptions in the humanitarian supply chain: A text mining approach for recruitment process.

Uncertainty and complexity have increased in recent decades, posing new challenges to humanitarian organisations. This study investigates whether using standard terminology in Human Resource Management processes can support the Humanitarian supply chain in attracting and maintaining highly skilled operators. We exploit text mining to compare job vacancies on ReliefWeb, the reference platform for humanitarian job seekers, and ESCO, the European Classification of Skills, Competencies, and Occupations. We measure the level of alignment in these two resources, providing quantitative evidence about terminology standardisation in job descriptions for supporting HR operators in the Humanitarian field. The most in-demand skills, besides languages, relate to resource management and economics and finance for capital management. Our results show that job vacancies for managerial and financial profiles are relatively more in line with the European database than those for technical profiles. However, the peculiarities of the humanitarian sector and the lack of standardisation are still a barrier to achieving the desired level of coherence with humanitarian policies.

Chemical genetics approaches for pesticide target mining

Chemical genetics approaches for pesticide target mining

Phosphonoalamides Reveal the Biosynthetic Origin of Phosphonoalanine Natural Products and a Convergent Pathway for Their Diversification

AbstractPhosphonate natural products, with their potent inhibitory activity, have found widespread use across multiple industries. Their success has inspired development of genome mining approaches that continue to reveal previously unknown bioactive scaffolds and biosynthetic insights. However, a greater understanding of phosphonate metabolism is required to enable prediction of compounds and their bioactivities from sequence information alone. Here, we expand our knowledge of this natural product class by reporting the complete biosynthesis of the phosphonoalamides, antimicrobial tripeptides with a conserved N‐terminal l‐phosphonoalanine (PnAla) residue produced by Streptomyces. The phosphonoalamides result from the convergence of PnAla biosynthesis and peptide ligation pathways. We elucidate the biochemistry underlying the transamination of phosphonopyruvate to PnAla, a new early branchpoint in phosphonate biosynthesis catalyzed by an aminotransferase with evolved specificity for phosphonate metabolism. Peptide formation is catalyzed by two ATP‐grasp ligases, the first of which produces dipeptides, and a second which ligates dipeptides to PnAla to produce phosphonoalamides. Substrate specificity profiling revealed a dramatic expansion of dipeptide and tripeptide products, while finding PnaC to be the most promiscuous dipeptide ligase reported thus far. Our findings highlight previously unknown transformations in natural product biosynthesis, promising enzyme biocatalysts, and unveil insights into the diversity of phosphonopeptide natural products.

Phosphonoalamides Reveal the Biosynthetic Origin of Phosphonoalanine Natural Products and a Convergent Pathway for Their Diversification.

Phosphonate natural products, with their potent inhibitory activity, have found widespread use across multiple industries. Their success has inspired development of genome mining approaches that continue to reveal previously unknown bioactive scaffolds and biosynthetic insights. However, a greater understanding of phosphonate metabolism is required to enable prediction of compounds and their bioactivities from sequence information alone. Here, we expand our knowledge of this natural product class by reporting the complete biosynthesis of the phosphonoalamides, antimicrobial tripeptides with a conserved N-terminal l-phosphonoalanine (PnAla) residue produced by Streptomyces. The phosphonoalamides result from the convergence of PnAla biosynthesis and peptide ligation pathways. We elucidate the biochemistry underlying the transamination of phosphonopyruvate to PnAla, a new early branchpoint in phosphonate biosynthesis catalyzed by an aminotransferase with evolved specificity for phosphonate metabolism. Peptide formation is catalyzed by two ATP-grasp ligases, the first of which produces dipeptides, and a second which ligates dipeptides to PnAla to produce phosphonoalamides. Substrate specificity profiling revealed a dramatic expansion of dipeptide and tripeptide products, while finding PnaC to be the most promiscuous dipeptide ligase reported thus far. Our findings highlight previously unknown transformations in natural product biosynthesis, promising enzyme biocatalysts, and unveil insights into the diversity of phosphonopeptide natural products.