Data Mining Analysis Research Articles

A prediction model to detect non-compliant taxpayers using a supervised machine learning approach: evidence from Tunisia

ABSTRACT This study aims to develop a tax non-compliance prediction model in Tunisia using supervised machine learning algorithms. A data mining analysis was conducted following the Knowledge Discovery in Databases (KDD) process, utilizing a dataset of 20,930 labeled observations from 2013 to 2017, comprising 110 attributes. We employed supervised learning algorithms, including K-Nearest Neighbors, Decision Trees, Naïve Bayes, Gradient Boosting, and Random Forest, to identify the most accurate model. Notably, Random Forest outperformed the other algorithms, achieving a prediction accuracy of 83%. Furthermore, through a combined interpretation of feature importance derived from Random Forest, SHAP value analysis, and ANOVA, our findings provide tax auditors with insights into the most influential attributes for predicting tax non-compliance. This study holds significant practical implications by enhancing the efficiency of tax audits and supporting tax authorities in their efforts to combat tax non-compliance.

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

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

Intermediate range order and two-state model: polyamorphism of GeO2 system insight from molecular dynamics data mining analytics

Intermediate range order and two-state model: polyamorphism of GeO2 system insight from molecular dynamics data mining analytics

High-Speed Imaging-Based Particle Attribute Analysis of Spray-Dried Amorphous Solid Dispersions Using a Convolution Neural Network.

Spray drying is a well-established method for preparing amorphous solid dispersion (ASD) formulations to improve the oral bioavailability of poorly soluble drugs. In addition to the characterization of the amorphous phase, particle attributes of spray-dried intermediates (SDIs), including particle size, morphology, and microstructure, need to be carefully studied and controlled for optimizing drug product performance. Although recent developments in microscopy technology have enabled the analysis of morphological attributes for individual SDI particles, a high-throughput method is highly desirable. In this work, a fingerprinting method exploiting high-speed dynamic imaging, laser diffraction (LD), and a convolutional neural network (CNN) was developed to characterize and quantify size and morphological distributions of particles in batches of spray-dried ASDs. This imaging technology enables the generation of hundreds of thousands of single-particle images in a few minutes that are analyzed by both unsupervised and supervised CNN models. The unsupervised data mining analysis demonstrated that a batch of SDI is a mixture of diverse particle subpopulations with varying sizes and morphological attributes. Motivated by this observation, we developed a CNN model that enabled rapid computation of the volumetric composition of the distinct particle subpopulations in a SDI batch, thus generating a morphological fingerprint. We implemented this high-speed imaging-based particle attribute analysis method to investigate SDIs containing hypromellose acetate succinate as a model system. The CNN fingerprint results enabled quantification of the changes in the morphological distribution of SDI batches prepared with variations in the spray drying process parameters, and the results were in line with the LD and electron microscopy data. Our experiments and analysis demonstrate the robustness and throughput of this fingerprinting approach for quantifying particle size and morphological distributions of individual SDI batches, which can help guide spray drying process development and thereby enable the development of a drug product with more robust process and optimized performance.

Identification of ETV5 as a prognostic marker related to epigenetic modification in pan-cancer and facilitates tumor progression in hepatocellular carcinoma

ETS variant transcription factor 5 (ETV5), a master transcription factor during development, exerts vital function on the occurrence and progression of various cancers. In order to systematically analyze and explore ETV5 potential specific regulatory mechanisms in pan-cancer, RNA sequencing data and clinicopathological features of patients with various tumors were obtained through the Cancer Genome Atlas (TCGA) and Genotype-Tissue Expression (GTEx) databases, and an integrated data mining analysis was carried out, including the association of ETV5 expression with patient prognosis, drug sensitivity and epigenetic modification. The results revealed that abnormally highly expressed ETV5 resulted in unfavorable prognosis and differential drug sensitivity in multiple malignancies, and its expression was associated with epigenetic modification modulators including EZH2. ETV5 related genes were enriched in tumorigenesis biological processes and signaling pathways. In hepatocellular carcinoma, ETV5 expression was correlated with patients’ tumor pathological stage and resulted in adverse outcome of patients. Our further experiments evidences indicated that ETV5 facilitated cell proliferation and reduced sensitivity to GSK126 via regulating EZH2. Collectively, this study comprehensively elucidates the carcinogenic effects and molecular mechanisms of ETV5 in tumorigenesis and development, and provides theoretical basis and guidance for tumor diagnosis, targeted therapy for ETV5 and clinical epigenetic drug research.

Towards the Implementation of Heuristics Miner in .Net Framework

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

Unveiling consumer satisfaction and its driving factors of EVs in China using an explainable artificial intelligence approach

As China’s electric vehicle (EV) industry shifts from policy-driven to market-oriented development, understanding post-purchase satisfaction and its driving factors becomes imperative. This study compiled objective product attributes and consumer online reviews for 1321 EV models from China’s largest automotive website, Autohome, covering the period between 2014 and 2022. By employing data mining and sentiment analysis (SA) techniques, this research extracted consumers’ overall satisfaction with EVs and identified the subjective product attributes that garnered the most attention in consumer online comments. Utilizing a machine learning (ML)—SHapley Additive exPlanations (SHAP) framework, the research pinpointed the most impactful objective and subjective product attributes on consumer satisfaction and ranked their impact intensity both statically and dynamically. The findings reveal that Chinese consumers are generally satisfied or very satisfied with their EVs. From a static perspective, distinctive objective product attributes of EVs, such as total motor power and range, play a crucial role in influencing consumer satisfaction. In terms of subjective product attributes, aspects like space, design, handling, and comfort are the most captivating to consumers and significantly shape their satisfaction. However, the dynamic analysis indicates that range anxiety persists, despite gradually increasing consumer satisfaction as the EV market matures. Additionally, price remains a crucial factor, particularly following the widespread implementation of subsidy withdrawal policies, making it the most sensitive factor for EV consumers. This study represents the first application of an explainable artificial intelligence framework to quantify the marginal impacts of various automotive product attributes on consumer satisfaction.

JYNNEOS vaccine safety surveillance in the vaccine safety datalink during the 2022 mpox outbreak in the United States.

The JYNNEOS vaccine (two doses given 28 days apart) was recommended in the United States for people at high risk of exposure to monkeypox virus during the 2022 mpox outbreak. Our objective was to assess the safety of JYNNEOS using two complementary epidemiologic methods. This observational cohort included patients of eight large integrated healthcare organizations who received JYNNEOS. Adverse events were identified using ICD-10 coded diagnoses assigned to medical visits. The first analysis used standardized incidence ratios (SIR) to compare the observed incidence of ten prespecified adverse events of special interest (AESI) during the 28 days after receipt of each dose of JYNNEOS to the expected incidence adjusted for several risk factors. The second analysis used tree-based data mining to identify temporal clustering of cases for more than 60,000 diagnoses and diagnosis groups within 70-days after JYNNEOS dose 1 administration. The SIR analysis included 53,583 adults who received JYNNEOS dose 1 and 38,206 who received dose 2. Males received 92% of the doses. There were no statistically significant elevated SIRs for any of the ten AESI. The tree-based data mining analysis included 36,912 vaccinees. Analysis of diagnoses in inpatient, emergency department, and outpatient settings identified statistically significant clusters of visits for rash and unspecified adverse effects. No new or unexpected safety concerns were identified. AESI did not occur more frequently than expected by chance alone. Non-serious medically attended adverse events, such as rash, have been previously reported and occurred infrequently.

Evaluating the roles of microRNAs associated with nonalcoholic fatty liver disease in hepatocellular carcinoma tumorigenesis: a systematic review and network analysis.

Non-alcoholic fatty liver disease (NAFLD) has become the leading cause of chronic liver disease worldwide. Hepatocellular carcinoma (HCC) is the fifth most common malignancy worldwide, with high morbidity and mortality. The rapidly increasing incidence of NAFLD is becoming an essential precursor of HCC globally. MicroRNAs (miRNAs) are involved in the progression of NAFLD and HCC. Potential miRNAs associated with NAFLD in HCC tumorigenesis were identified through a systematic review, and their roles were evaluated by data mining analysis. The biological function of the potential miRNA and its target genes in NAFLD and HCC were evaluated by bioinformatic analysis. MIR122 was identified as the potential miRNA associated with NAFLD and HCC. Then, MIR122 expression was significantly lower in HCC patients, and higher MIR122 levels were associated with significantly better overall survival. Next, the biological functions of MIR122 and target genes were predicted to be involved in inflammation, fibrosis, cell proliferation, invasion, metastasis, and apoptosis. In particular, the FOXO signaling pathway may regulate the above biological functions. MIR122 was suggested to be involved in progressing from NAFLD to HCC through the PI3K/AKT/FOXO pathway. PROSPERO, identifier: CRD 42024517940.

Positioning Sensor Data Mining and Correlation Analysis Based on Multi-mode Radio Frequency Identification

Real-time positioning and sensor data mining are critical for various Internet of things (IoT) applications, but current approaches face challenges such as limited accuracy, high cost, and energy inefficiency. This paper proposes a novel fusion intelligent structure that combines radio frequency identification (RFID) technology and wireless sensor networks (WSN) to enable accurate and efficient positioning and data mining. The proposed method consists of two key components: an energy heterogeneity strategy for optimizing network energy consumption, and a data association feature analysis technique for mining sensor data. The results demonstrated that the proposed approach achieved superior positioning accuracy compared to other algorithms, with an average error of less than 0.300 under various conditions. The data detection accuracy was also high, with a maximum false detection rate of 3%. Furthermore, the proposed energy heterogeneity strategy significantly improved network energy utilization and stability. Real-world scenario testing validated the practicality of the proposed approach, with an average positioning error of less than 0.500 meters. These results validate the effectiveness of the proposed RFID-WSN fusion structure for real-time positioning and sensor data mining, providing a promising solution for IoT applications.

Fault-tolerant graph embeddings in Archimedean networks

Fault tolerance refers to the ability of a system to continue functioning even if some of its components fail. This concept is fundamental in several domains because reliability and continuous operation are essential in carrying out their functions. Graph embedding means mapping a graph into some other structure that preserves some of the properties or relations held by the original graph. Applications in machine learning, data mining, and network analysis make fault-tolerant embedding of graphs a crucial topic. In this paper, fault-tolerant embeddings are proposed in Archimedean tessellations. The path in the embeddings does not intersect or overlap.

Inner product reduction for fuzzy formal contexts

Formal concept analysis finds application across multiple domains, including knowledge representation, data mining, and decision analysis. Within this framework, the exploration of attribute reduction for fuzzy formal contexts represents a substantial area of research. We introduce a novel form of attribute reduction for fuzzy formal contexts named inner product reduction, and an algorithm for finding all inner product reducts is given by using the indiscernibility matrix, and a calculation example is given. Furthermore, for consistent fuzzy decision formal contexts, the definition and algorithm of inner product reduction are given. Finally, the concept and algorithm of inner product reduction are extended to general fuzzy decision formal contexts. Through experimental verification, the viability and efficacy of the inner product reduction algorithm for fuzzy formal contexts are verified.

The dry lab microscopist or prompt microscopist: do we need them?

AbstractIn modern biological microscopy, the explosion of data volume and complexity highlights the urgent need for specialised data management support roles. While traditional microscopy focuses on visual data presentation, the rapid increase in big data acquisition and data mining demands advanced handling and analysis. This gap underscores the need for “dry lab microscopists” or data experts skilled in microscopy data management, software interoperability, and AI-driven solutions. Job markets reflect this demand, pointing to the necessity for dedicated training programs. Integrating these specialists into research institutions is crucial for addressing digital data challenges and maintaining high standards in data integrity and analysis. Their role is essential for advancing research in the data-driven era.

VDGE: a data repository of variation database for gene-edited animals across multiple species.

Gene-edited animals are crucial for addressing fundamental questions in biology and medicine and hold promise for practical applications. In light of the rapid advancement of gene editing technologies over the past decade, a dramatically increased number of gene-edited animals have been generated. Genome editing at off-target sites can, however, introduce genomic variations, potentially leading to unintended functional consequences in these animals. So, there is an urgent need to systematically collect and collate these variations in gene-edited animals to aid data mining and integrative in-depth analyses. However, existing databases are currently insufficient to meet this need. Here, we present the Variation Database of Gene-Edited animals (VDGE, https://ngdc.cncb.ac.cn/vdge), the first open-access repository to present genomic variations and annotations in gene-edited animals, with a particular focus on larger animals such as monkeys. At present, VDGE houses 151 on-target mutations from 210 samples, and 115,710 variations identified from 107 gene-edited and wild-type animal trios through unified and standardized analysis and concurrently provides comprehensive annotation details for each variation, thus facilitating the assessment of their functional consequences and promoting mechanistic studies and practical applications for gene-edited animals.

In silico-guided synthesis of a new, highly soluble, and anti-melanoma flavone glucoside: Skullcapflavone II-6'-O-β-glucoside.

Guided by in silico analysis tools and biotransformation technology, new derivatives of natural compounds with heightened bioactivities can be explored and synthesized efficiently. In this study, in silico data mining and molecular docking analysis predicted that glucosides of skullcapflavone II (SKII) were new flavonoid compounds and had higher binding potential to oncogenic proteins than SKII. These benefits guided us to perform glycosylation of SKII by utilizing four glycoside hydrolases and five glycosyltransferases (GTs). Findings unveiled that exclusive glycosylation of SKII was achieved solely through the action of GTs, with Bacillus subtilis BsUGT489 exhibiting the highest catalytic glycosylation efficacy. Structure analysis determined the glycosylated product as a novel compound, skullcapflavone II-6'-O-β-glucoside (SKII-G). Significantly, the aqueous solubility of SKII-G exceeded its precursor, SKII, by 272-fold. Furthermore, SKII-G demonstrated noteworthy anti-melanoma activity against human A2058 cells, exhibiting an IC50 value surpassing that of SKII by 1.4-fold. Intriguingly, no substantial cytotoxic effects were observed in a murine macrophage cell line, RAW 264.7. This promising anti-melanoma activity without adverse effects on macrophages suggests that SKII-G could be a potential candidate for further preclinical and clinical studies. The in silico tool-guided synthesis of a new, highly soluble, and potent anti-melanoma glucoside, SKII-G, provides a rational design to facilitate the future discovery of new and bioactive compounds.

Trend Analysis of Fluency-Related Research Articles: Using Data Mining

This research seeks to identify recent research trends in analysing fluency in English language studies since 2010. The importance of studying corpora that compile registered research in linguistics is growing; thus, it is time to consider the significance of data mining analysis on the corpora. Considering this emerging research topic, this analysis intends to generate and compare word clouds and word metric charts from speaking and writing abstract corpora in linguistics research centred on the keyword ‘Fluency’. This comparison is minimally addressed in extant research; hence, this investigation aims to fill this gap. The corpus contains 50 speaking and 15 writing abstracts from linguistics journals. To create the word cloud, AntConc4.1.4 software was used to analyse the corpora, while TF-IDF and matrix analysis were conducted using R. As a result, in spoken English, ‘fluency’ studies were largely related to 'teaching' and tended to be dominated by studies focusing on ‘fluency’ alone. In contrast, writing studies were mostly related to learner proficiency and assessment, and many studies analysed the relationship between linguistic abilities by expanding the scope of ‘fluency’ to include ‘accuracy’ and ‘complexity’. This study will benefit researchers in deciding on topics as it provides research directions and trends in analysing fluency in the two interconnected but differently expressed fields (i.e., speaking and writing).

THI1 Gene Evolutionary Trends: A Comprehensive Plant-Focused Assessment via Data Mining and Large-Scale Analysis.

Molecular evolution analysis typically involves identifying selection pressure and reconstructing evolutionary trends. This process usually requires access to specific data related to a target gene or gene family within a particular group of organisms. While recent advancements in high-throughput sequencing techniques have resulted in the rapid accumulation of extensive genomics and transcriptomics data and the creation of new databases in public repositories, extracting valuable insights from such vast data sets remains a significant challenge for researchers. Here, we elucidated the evolutionary history of THI1, a gene responsible for encoding thiamine thiazole synthase. The thiazole ring is a precursor for vitamin B1 and a crucial cofactor in primary metabolic pathways. A thorough search of complete genomes available within public repositories reveals 702 THI1 homologs of Archaea and Eukarya. Throughout its diversification, the plant lineage has preserved the THI1 gene by incorporating the N-terminus and targeting the chloroplasts. Likewise, evolutionary pressures and lifestyle appear to be associated with retention of TPP riboswitch sites and consequent dual posttranscriptional regulation of the de novo biosynthesis pathway in basal groups. Multicopy retention of THI1 is not a typical plant pattern, even after successive genome duplications. Examining cis-regulatory sites in plants uncovers two shared motifs across all plant lineages. A data mining of 484 transcriptome data sets supports the THI1 homolog expression under a light/dark cycle response and a tissue-specific pattern. Finally, the work presented brings a new look at public repositories as an opportunity to explore evolutionary trends to THI1.

A secure Multi-Frequency Computation Protocol in 2-Part Fully Distributed Setting

Secure frequency computation protocols have been researched and applied to address various privacy-preserving problems in machine learning, data mining, and data analysis. However, these protocols only allow for the calculation of a single frequency value in one execution. In this paper, we propose a protocol for calculating multiple secure frequency values concurrently for the 2PFD data model, which is a relatively new distributed data model that has appeared in many practical problems but has not received much attention. The proposed protocol not only maintains the accuracy of the output results and a high level of security but also exhibits good performance.

The Role of Data Analytics in Enhancing Public Administration in Europe

Sustainable development (SD) represents a growth approach that tries to maintain a social, economic and environmental balance. SD aims to meet the needs of the present without compromising the needs of future generations. For a sustainable development, a key element is represented by renewable energy (RE). The use of RE on an increasingly large scale brings with it a series of advantages and positively influences aspects such as resource conservation, air and water quality improvement, climate change, greenhouse gas emissions, etc. Realization of RE through different ways such as wind energy, solar power, hydropower, etc. and by combining them, European citizens can take an important step in realizing a more sustainable and renewable energy future. The article presents a data mining analysis on the use of RE in EU countries, taking into account the share of industry use such as heating and cooling, transport and electricity. The results of the analysis aim to identify countries that show a similar behavior from the point of view of the use of RE. Based on them, policies and strategies at the EU level can be founded. Keywords: renewable energy, sustainable development, European Union, data mining

Analyzing failure mechanisms and predicting step-like displacement: Rainfall and RWL dynamics in lock-unlock landslides

Lock-unlock landslides have thick sliding zones that store a lot of energy. This makes them start quickly, happen suddenly, and have serious consequences. Therefore, it becomes urgent to study the deformation and failure mechanisms of such landslides and develop rational predictive models. Taking the Jiuxianping landslide as an example, this study investigates the regularity of landslide displacement changes using multi-source data, focusing on the abrupt displacement patterns in the unlock phase. Furthermore, employing Transient Release and Inhalation Method tests combined with Geo-Studio’s SEEP/W and SIGMA/W modules for fluid–solid coupled simulation calculations, the evolution process of landslide failure mechanisms and deformation characteristics is analyzed and discussed. Lastly, utilizing data mining analysis of multi-source data, a hybrid optimized machine learning predictive model is established for model prediction comparison. The study reveals that: (1) The rise in infiltration line elevates pore water pressure, affecting the stability of the sliding zone, leading to “unlock effects” and step-like displacement deformation; (2) Simulation shows that YY208 is closer to the actual situation, located at the far bank position, while YY210 is greatly influenced by the “buoyancy effect”, resulting in a slowdown in deformation velocity; (3) After data preprocessing, overall actual displacement prediction performs better than simulation displacement prediction in terms of Mean Absolute Error, Mean Squared Error and Correlation Coefficient, but noise reduction processing can improve the periodic prediction effect of simulation displacement.