Data Mining Analysis Research Articles

Risk Analysis and Establishment of Supervision System of Internet Finance Based on Big Data Era

The benefits of Internet finance, such as its speed, transparency, and efficiency, have caused conventional financial institutions to rethink their business models and have led to its tremendous growth in recent years. However, as Internet finance continues to grow, new possibilities and threats are continuously developing. One of the most pressing concerns in the use of Internet technology for financial growth is how to properly identify and evaluate risks involved for Internet finance, as well as how to accurately anticipate such risks. Internet finance risk elements are examined thoroughly in this research, and a feasible solution to reduce Internet financial hazards is proposed. This paper completes the following work: (1) according to the collected sample data, the BP network is used as a big data mining analysis method to establish a financial risk assessment model. (2) The data is processed accordingly, and then based on the MATLAB program platform, the BP network numerical calculation is built to train the theoretical model, and the actual output and predicted output are obtained. (3) With the analysis results of data mining, this work has established a risk prevention and control supervision system. (4) This work has carried out various experiments on the designed method, and the results have verified the superiority of the method.

Combined toxicity assessment of a naturally occurring toxin and a triazole fungicide on different biological processes through toxicogenomic data mining with mixtures

Fungicides are widely used to prevent fungal growth and reduce mycotoxin contamination in food, which provides the opportunity for the co-occurrence of mycotoxins and fungicide residues in food and poses a greater risk to human health. To assess the combined effects of a naturally occurring mycotoxin, citrinin (CIT), and a widely used triazole fungicide, triadimefon (TAD) on different biological processes, the comparative toxicogenomics database was used to obtain phenotypes and response genes for CIT or TAD exposure. Then individual and combined exposure models were developed with zebrafish embryos, and the interaction between CIT and TAD was analyzed using the 2 × 2 factorial design approach to observe the toxic effects. Through data mining analysis, our results showed that CIT or TAD exposure is related to different biological phenotypes, such as cell death, regulation of antioxidant systems, and thyroid hormone metabolism. Our results also showed that CIT (4-day LC50 value of 12.7 mg/L) exposure possessed higher toxicity to zebrafish embryos compared with TAD (4-day LC50 value of 29.6 mg/L). Meanwhile, individual exposure to CIT and TAD altered the expression levels of biomarkers related to oxidative stress, inflammation, apoptosis and hypothalamic-pituitary-thyroid (HPT) axis. Notably, combined exposure to CIT and TAD induced changes in the mentioned biological processes and had an interactive effect on the expression of multiple biomarkers. In conclusion, we evaluated the toxic effects of CIT and TAD in isolation and combination by in-vivo experiments, which provide a new methodological basis and reference for future risk assessment and setting of safety limits for foodborne toxicants.

Market Analysis for Farmers using Machine Learning

Using big data Data mining and predictive analysis have developed to be helpful for examining crop prices in agriculture. This paper considers applying methods of Big Data and data mining utilising agricultural data. As a result of an outdated chain structure for selling the crops in their various markets, farmers are increasingly concerned with getting the full worth of the commodity. Due to the fact that farmers in the area may only sell their goods in a way that indirectly affects consumers, the market's true potential is still untapped. E-agriculture is a growing industry that focuses on improving farming and advancing provincial development through better data and correspondence forms. The market has a growing amount of data, just as other industries. Data from the various markets in the Bangalore area are taken into account and employed in this work's data mining decision tree models. Farmers are the backbone of our nation, which is dealing with a number of issues. Among these issues, getting pertinent information about the crop and weather specifics at the appropriate moment is one of the most significant. The primary objective of the Map-Reduce-based decision tree model is to give Farmers the greatest price for their product. In comparison to other models, the output of the proposed Map Reduce model is more accurate at predicting the best price from the existing market data.

COMPARISON OF NAÏVE BAYES AND KNN ALGORITHMS IN THE ANALYSIS OF PUBLIC SENTIMENT REGARDING THE IMPLEMENTATION OF GOVERNMENT EMPLOYEES WITH TEACHER WORK AGREEMENTS

Until now the implementation of education in Indonesia cannot be separated from the complexity of the management of educators, one of which is honorary teachers, and bureaucratic reform which has quite an impact on the quality of education and the work climate in it. As a way to increase public service satisfaction through the state civil apparatus (ASN), the Indonesian Ministry of Education and Culture agreed with the Ministry of Administrative Reform and Bureaucratic Reform and the Ministry of Finance to change the recruitment system or appointment of government employee teachers from the acceptance of prospective Civil Servants. Civil servants (CPNS) become government employees with a work agreement (PPPK) which in its implementation there are still obstacles and pros and cons, some agree and some disagree. therefore the researcher conducted research on sentiment analysis in data mining in the implementation of PPPK teachers on social media Twitter as many as 871 data which were then processed into 519 data. the author uses the Naïve Bayes and KNN techniques to determine the predictive effect of the Naïve Bayes and KNN algorithms on public opinion in the implementation of first aid instructors and compares the level of accuracy of the 2 methods. Researchers use the RapidMiner tool version nine.10.1. The prediction results of Naïve Bayes are 328 statistics with positive or agree sentiment and 191 information with negative sentiment, and the last is the prediction result from KNN, namely 315 information with positive sentiment and 204 facts with negative sentiment. analysis of public sentiment on the implementation of teacher first resource on social media Twitter with the Naïve Bayes algorithm achieves an accuracy of 75.53%. And the KNN achieves an accuracy of 73.41%. In this study, the Naïve Bayes method is a technique with a higher level of accuracy than the KNN with an accuracy rate of 75.53%.

Association rules and decision rules

AbstractDetermining association rules of significant interest is an essential task within data mining and statistical analysis. In this paper, we first precisely define the notion of association rule. For this, we introduce a general model, which includes the usual transaction model, and which allows many operations on the association rules. Then, we interpret association rules as statistical decision rules. This interpretation leads to four decisional measures, one of them being the usual confidence. Then, we give some strategies based on the use of these four decisional measures in order to select or to construct association rules with a given consequent. We finally present an experimental study to illustrate these strategies. This study is carried out in R language, with the R‐package we specifically built for association rules mining.

Uncovering the Depletion Patterns of Inland Water Bodies via Remote Sensing, Data Mining, and Statistical Analysis

Addressing the issue of shrinking saline lakes around the globe has turned into one of the most pressing issues for sustainable water resource management. While it has been established that natural climate variability, human interference, climate change, or a combination of these factors can lead to the depletion of saline lakes, it is crucial to investigate each case and diagnose the potential causes of this devastating phenomenon. On that note, this study aims to promote a comprehensive analytical framework that can reveal any significant depletion patterns in lakes while analyzing the potential reasons behind these observed changes. The methodology used in this study is based on statistical analysis, data mining techniques, and remote sensing-based datasets. To achieve the objective of this study, Maharlou Lake has been selected to demonstrate the application of the proposed framework. The results revealed two types of depletion patterns in the lake’s surface area: a sharp breaking point in 2007/2008 and a gradual negative trend, which was more pronounced in dry seasons and less prominent in wet seasons. Furthermore, the analysis of hydro-climatic variables has indicated the presence of abrupt and gradual changes in these variables’ time series, which could be interpreted as a signal that climate change and anthropogenic drought are changing the basin’s status quo. Lastly, analyzing the statistically significant correlation between hydro-climatic variables and the lake’s surface area showed the potential connection between the observed changing patterns. The results obtained from data mining models suggest that Maharlou Lake has undergone a morphological transformation and is currently adopting these new conditions. If preventive measures are not taken to revive Maharlou Lake, the tipping point might have been reached, and reviving the lake could be improbable, if not impossible.

Composition analysis and identification of ancient glass products based on gray correlation

The study of ancient glass, as an important branch of scientific and technological archaeology, is an important physical material for exploring the economic, technological and cultural exchanges between China and foreign countries on the Silk Road. It is of great significance for the study of the development of ancient societies and cultural exchanges between China and foreign countries. This paper focuses on the composition analysis and identification of ancient glass products, based on data mining and software analysis, giving the weathering pattern of glass surface, predicting the chemical composition content before weathering, as well as cluster analysis and correlation analysis of different categories of glass and their chemical composition. We also concluded that the composition of silica, potassium oxide and barium oxide in high potassium glass artifacts changed to a great extent before and after weathering, while the composition of silica and lead oxide in lead-barium glass artifacts changed to a great extent, and finally, we constructed a multiple linear regression model for prediction by the data of each chemical composition at the weathering point, and conducted F-test on the model to prove that the prediction models of silica, potassium oxide, barium oxide and lead oxide had a good performance. The F-test of the model proved the reasonableness of the prediction models for silica, potassium oxide, barium oxide, and lead oxide. It can be concluded that the glass type has an influence on the chemical composition of glass, so the glass can be divided into two categories of glass: high potassium and lead-barium, and then the chemical composition of these two categories of glass were analyzed separately by gray correlation analysis to obtain the top five correlation ranking of the chemical composition of each category of glass, and then the differences in the chemical composition of these two categories of glass were compared.

Identifying microbial signatures for patients with postmenopausal osteoporosis using gut microbiota analyses and feature selection approaches.

Osteoporosis (OP) is a metabolic bone disorder characterized by low bone mass and deterioration of micro-architectural bone tissue. The most common type of OP is postmenopausal osteoporosis (PMOP), with fragility fractures becoming a global burden for women. Recently, the gut microbiota has been connected to bone metabolism. The aim of this study was to characterize the gut microbiota signatures in PMOP patients and controls. Fecal samples from 21 PMOP patients and 37 controls were collected and analyzed using amplicon sequencing of the V3-V4 regions of the 16S rRNA gene. The bone mineral density (BMD) measurement and laboratory biochemical test were performed on all participants. Two feature selection algorithms, maximal information coefficient (MIC) and XGBoost, were employed to identify the PMOP-related microbial features. Results showed that the composition of gut microbiota changed in PMOP patients, and microbial abundances were more correlated with total hip BMD/T-score than lumbar spine BMD/T-score. Using the MIC and XGBoost methods, we identified a set of PMOP-related microbes; a logistic regression model revealed that two microbial markers (Fusobacteria and Lactobacillaceae) had significant abilities in disease classification between the PMOP and control groups. Taken together, the findings of this study provide new insights into the etiology of OP/PMOP, as well as modulating gut microbiota as a therapeutic target in the diseases. We also highlight the application of feature selection approaches in biological data mining and data analysis, which may improve the research in medical and life sciences.

Data mining and analysis for predicting electrical energy consumption

In this study paper, the feasibility of constructing a complete smart system for anticipating electrical power consumption is created, as electricity's market share is expected to expand over the future decades. Smart grids and smart meters will help utility companies and their customers soon. New services and businesses in energy management need software development and data analytics skills. New services and enterprises are competitive. The project's electricity consumers are categorized by their hourly power usage percentage. This classification was done using data mining (five algorithms in specific) and data analysis theory. This division aims to help each group minimize energy use and expenditures, encourage energy-saving activities, and promote consumer involvement by giving tailored guidance. The intended segmentation is done through an iterative process using a computer classification computation, post-analysis, and data mining with visualization and statistical methodologies.

Review on Data Mining and Data Analysis Method for Adolescent Suicide Problem

This paper suggested that both positive and negative family factors can impact adolescent suicide rates. Supportive relationships with parents, siblings, and other family members can provide a sense of belonging, connection, and emotional support that can help to protect adolescents from suicidal thoughts and behaviors. Studies have found that adolescents who are exposed to these types of adverse family experiences are more likely to experience depression, anxiety, and other mental health problems, which can increase their risk of suicide. The research presented in this article suggests that family environment continues to be one of the most important factors influencing adolescent suicide rates, with the two groups most at risk for suicide having much higher levels of exposure to domestic violence and substance abuse. No significant changes were found in age, academic achievement, race, or family structure. This suggests that the most influential determinants of adolescent suicide rates are family environment, followed by gender and prior exposure to suicide. The purpose of this literature review on adolescent suicide is to provide a comprehensive overview of existing research on the influence of relationships and family on adolescent suicide rates, highlight key findings and identify areas for further research.

A Study of Prediction Accuracy of English Test Performance Using Data Mining and Analysis

This paper focused on the effect of data mining in predicting students' English test scores. With the progress of data mining analysis, there are more applications in teaching, and data mining to achieve the prediction of students’ test scores is important to support the educational work. In this paper, the C4.5 decision tree algorithm was improved by combining Taylor's series, and then the data of students' English tests in 2019-2020 were collected for experiments. The results showed that the scores of “Comprehensive English” and “Specialized English” had a great influence on the score of CET-4, and the improved C4.5 algorithm was more efficient than the original one, maintained a fast computation speed even when the data volume was large, and had an accuracy of more than 85%. The results demonstrate the accuracy of the improved C4.5 algorithm for predicting students’ English test scores. The improved C4.5 algorithm can be extended and used in reality.

ANALISIS JARINGAN KOMUNIKASI HOLYWINGS PADA PROMOSI MUHAMMAD-MARIA DI TWITTER

This study is aim for map communication network formed when Holywings company got Public Relation Crisis during their product campaign using Muhammad Maria in Social Media Twitter. This issue have been considered by community as a religious blasphemy. This research aim to determine actors who control the information in this issue which lead actors can influence audience’s sentiment in the issue itself. This actors will create a cluster who will affect Holywings corporate image in Public Relations theory. Researchers used a quantitative research methods with a descriptive approach in conducting this research. This research use NodeXL as software for data mining and data analysis for find metrics and actors inside the network. This method used since conversation in internet era cannot analyzed in tradisional technique. Based on analysis that has been done there are 3 main actors @imanlagi, @catchmeupid dan @knpiharis. In communication network there are 3 main clusters created.

Prediksi Masa Studi Mahasiswa Unama Jambi Menggunakan Metode Algoritma C4.5

Every year the number of students at The University of Dynamics of the Nation jambi is always increasing but the students who graduate are different from the number of students who enter. Therefore, the author conducts a data mining analysis on student data so that it can be used by academic supervisors to find out the graduation status of students and as a warning so that students can graduate on time so as to reduce the number of delays in graduation. The author uses student data in 2016 and 2017 as training data and 2020 as testing data as many as 120 training data and 109 testing data and has carried out the data cleaning and attribute selection process using the forward selection method. In conducting the analysis, the author used the Tools Weka tool. The author uses the C4.5 algorithm method with 12 attributes, but there are 4 attributes that are most influential after selecting data using the forward selection method on WEKA. In this case, the author uses 4 test options, namely 5 Fold Cross Validation, 10 Fold Cross Validation, 70% Percentage Split, and 80% Percentage Split. The C4.5 Algorithm method produces the largest accuracy value in the training data, namely 5 Fold Cross Validation by 92.5% and in the testing data by 100%.

Using a Data Mining Method to Explore Strategies for Improving the Social Interaction Environment Quality of Urban Neighborhood Open Spaces

With the intensification of population aging and the increasing awareness of public health protection in the post-epidemic era, the renewal of the old urban community neighborhood space is facing many new challenges and problems. Neighborhood Public Open Space (POS) is the main place for people to carry out various social activities in community life. The quality of the social interaction environment that a neighborhood POS can provide can have a vital impact on people’s well-being, as well as their physical and mental health. Therefore, the purpose of this research is to identify and clarify the key physical environmental design attributes/features of the old urban community neighborhood POS, and to explore the relationship between them from the perspective of creating a high-quality social environment. Through the investigation of relevant cases in Shenzhen and Guangzhou, China, the classification performance of each case on the key physical and environmental elements is used as the conditional attribute, and the quality of the social interaction environment in the current situation of each case is used as the decision making attribute to conduct a data mining analysis. Using rough set theory, this study screened out four important elements: greenbelt form planning (C1); ped and bike system (C2); space organization and zoning planning (C6); Public facilities (C8). Moreover, this study also presents a set of hierarchical decision rules to describe the classification status of the matching physical environmental design elements when the social interaction environment reaches a high quality in the neighborhood POS. This study provides local policy makers with key current situation assessment and diagnostic tools in urban-built environmental renewal projects. The results of this study can help designers draw up the renovation design plans of neighborhood POS on the basis of efficiently obtaining the practical experience of relevant cases, and then create a high-quality social interaction environment.

A New Quantum Private Protocol for Set Intersection Cardinality Based on a Quantum Homomorphic Encryption Scheme for Toffoli Gate

Set Intersection Cardinality (SI-CA) computes the intersection cardinality of two parties' sets, which has many important and practical applications such as data mining and data analysis. However, in the face of big data sets, it is difficult for two parties to execute the SI-CA protocol repeatedly. In order to reduce the execution pressure, a Private Set Intersection Cardinality (PSI-CA) protocol based on a quantum homomorphic encryption scheme for the Toffoli gate is proposed. Two parties encode their private sets into two quantum sequences and encrypt their sequences by way of a quantum homomorphic encryption scheme. After receiving the encrypted results, the semi-honest third party (TP) can determine the equality of two quantum sequences with the Toffoli gate and decrypted keys. The simulation of the quantum homomorphic encryption scheme for the Toffoli gate on two quantum bits is given by the IBM Quantum Experience platform. The simulation results show that the scheme can also realize the corresponding function on two quantum sequences.

Architecture-Oriented Agent-Based Simulations and Machine Learning Solution: The Case of Tsunami Emergency Analysis for Local Decision Makers

Tsunamis are a perilous natural phenomenon endangering growing coastal populations and tourists in many seaside resorts. Failures in responding to recent tsunami events stresses the importance of further research in building a robust tsunami warning system, especially in the “last mile” component. The lack of detail, unification and standardisation in information processing and decision support hampers wider implementation of reusable information technology solutions among local authorities and officials. In this paper, the architecture of a tsunami emergency solution is introduced. The aim of the research is to present a tsunami emergency solution for local authorities and officials responsible for preparing tsunami response and evacuation plans. The solution is based on a combination of machine learning techniques and agent-based modelling, enabling analysis of both real and simulated datasets. The solution is designed and developed based on the principles of enterprise architecture development. The data exploration follows the practices for data mining and big data analyses. The architecture of the solution is depicted using the standardised notation and includes components that can be exploited by responsible local authorities to test various tsunami impact scenarios and prepare plans for appropriate response measures.

ScGAD: a new task and end-to-end framework for generalized cell type annotation and discovery.

The rapid development of single-cell RNA sequencing (scRNA-seq) technology allows us to study gene expression heterogeneity at the cellular level. Cell annotation is the basis for subsequent downstream analysis in single-cell data mining. As more and more well-annotated scRNA-seq reference data become available, many automatic annotation methods have sprung up in order to simplify the cell annotation process on unlabeled target data. However, existing methods rarely explore the fine-grained semantic knowledge of novel cell types absent from the reference data, and they are usually susceptible to batch effects on the classification of seen cell types. Taking into consideration the limitations above, this paper proposes a new and practical task called generalized cell type annotation and discovery for scRNA-seq data whereby target cells are labeled with either seen cell types or cluster labels, instead of a unified 'unassigned' label. To accomplish this, we carefully design a comprehensive evaluation benchmark and propose a novel end-to-end algorithmic framework called scGAD. Specifically, scGAD first builds the intrinsic correspondences on seen and novel cell types by retrieving geometrically and semantically mutual nearest neighbors as anchor pairs. Together with the similarity affinity score, a soft anchor-based self-supervised learning module is then designed to transfer the known label information from reference data to target data and aggregate the new semantic knowledge within target data in the prediction space. To enhance the inter-type separation and intra-type compactness, we further propose a confidential prototype self-supervised learning paradigm to implicitly capture the global topological structure of cells in the embedding space. Such a bidirectional dual alignment mechanism between embedding space and prediction space can better handle batch effect and cell type shift. Extensive results on massive simulation datasets and real datasets demonstrate the superiority of scGAD over various state-of-the-art clustering and annotation methods. We also implement marker gene identification to validate the effectiveness of scGAD in clustering novel cell types and their biological significance. To the best of our knowledge, we are the first to introduce this new and practical task and propose an end-to-end algorithmic framework to solve it. Our method scGAD is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/aimeeyaoyao/scGAD.

A bacterial sulfoglycosidase highlights mucin O-glycan breakdown in the gut ecosystem.

Mucinolytic bacteria modulate host-microbiota symbiosis and dysbiosis through their ability to degrade mucin O-glycans. However, how and to what extent bacterial enzymes are involved in the breakdown process remains poorly understood. Here we focus on a glycoside hydrolase family 20 sulfoglycosidase (BbhII) from Bifidobacterium bifidum, which releases N-acetylglucosamine-6-sulfate from sulfated mucins. Glycomic analysis showed that, in addition to sulfatases, sulfoglycosidases are involved in mucin O-glycan breakdown in vivo and that the released N-acetylglucosamine-6-sulfate potentially affects gut microbial metabolism, both of which were also supported by a metagenomic data mining analysis. Enzymatic and structural analysis of BbhII reveals the architecture underlying its specificity and the presence of a GlcNAc-6S-specific carbohydrate-binding module (CBM) 32 with a distinct sugar recognition mode that B. bifidum takes advantage of to degrade mucin O-glycans. Comparative analysis of the genomes of prominent mucinolytic bacteria also highlights a CBM-dependent O-glycan breakdown strategy used by B. bifidum.

Deciphering Target Protein Cascade in Salmonella typhi Biofilm using Genomic Data Mining, and Protein-protein Interaction.

Salmonella typhi biofilm confers a serious public health issue for lengthy periods and the rise in antibiotic resistance and death rate. Biofilm generation has rendered even the most potent antibiotics ineffective in controlling the illness, and the S. typhi outbreak has turned into a fatal disease typhoid. S. typhi infection has also been connected to other deadly illnesses, such as a gall bladder cancer. The virulence of this disease is due to the interaction of numerous genes and proteins of S. typhi. The study aimed to identify a cascade of target proteins in S. typhi biofilm condition with the help of genomic data mining and protein-protein interaction analysis. The goal of this study was to notice some important pharmacological targets in S. typhi. using genomic data mining, and protein-protein interaction approaches were used so that new drugs could be developed to combat the disease. In this study, we identified 15 potential target proteins that are critical for S. typhi biofilm growth and maturation. Three proteins, CsgD, AdrA, and BcsA, were deciphered with their significant role in the synthesis of cellulose, a critical component of biofilm's extracellular matrix. The CsgD protein was also shown to have high interconnectedness and strong interactions with other important target proteins of S. typhi. As a result, it has been concluded that CsgD is involved in a range of activities, including cellulose synthesis, bacterial pathogenicity, quorum sensing, and bacterial virulence. All identified targets in this study possess hydrophobic properties, and their cellular localization offered proof of a potent therapeutic target. Overall results of this study, drug target shortage in S. typhi is also spotlighted, and we believe that obtained result could be useful for the design and development of some potent anti-salmonella agents for typhoid fever in the future.

CLUSTERIZATION OF DATA ARRAYS BASED ON THE MODIFIED GRAY WOLF ALGORITHM

Context. The task of clustering arrays of multidimensional data, the main goal of which is to find classes of observations that are homogeneous in the sense of the accepted metric, is an important part of the intelligent data analysis of Data Mining. From a computational point of view, the problem of clustering turns into the problem of finding local extrema of a multiextreme function, which are repeatedly started from different points of the original data array. To speed up the process of finding these extrema using the ideas of evolutionary optimization, which includes algorithms inspired by nature, swarm algorithms, population algorithms, etc.
 Objective. The purpose of the work is to introduce a procedure for clustering data arrays based on the improved gray wolf algorithm.
 Method. A method of clustering data arrays based on the modified gray wolf algorithm is introduced. The advantage of the proposed approach is a reduction in the time of solving optimization problems in conditions where clusters are overlap. A feature of the proposed method is computational simplicity and high speed, due to the fact that the entire array is processed only once, that is, eliminates the need for multi-era self-learning, implemented in traditional fuzzy clustering algorithms.
 Results. The results of the experiments confirm the effectiveness of the proposed approach in clustering problems under the condition of classes that overlap and allow us to recommend the proposed method for use in practice to solve problems of automatic clustering big data.
 Conclusions. A method of clustering data arrays based on the modified gray wolf algorithm is introduced. The advantage of the proposed approach is the reduction of time for solving optimization problems. The results of the experiments confirm the effectiveness of the proposed approach in clustering problems under the conditions of overlapping clusters.