Computational Data Mining Research Articles

The communicative dimension of graphic design elements - Such as infographics

The purpose of the current study is to address a research question about the role that visual design elements have in communication. The data were collected based on their technical relevance, which highlights the general description of the field of research that includes graphics, infographics in the field of communication, and elements of visual design Review of the relevant literature and concepts: To begin with, we must consider the communication aspects of the design in order to produce truly successful visual design elements. The communicative dimension of graphic design elements such as infographics are invaluable in conveying information in a clear and engaging way. Two opened the way for the expansion of the use of visual elements in the manufacture of the media message. This study discusses the communicative dimensions of visual design elements, in general, and infographics in particular, as infographic is part of information visualization. This study discusses the communicative dimensions of visual design elements, in general, and infographics in particular, as Infographic is part of information visualization, in addition to that it is a research field related to communication as it focuses on patterns and trends in abstract data sets, and the field of infographic design, and information visualization combines the concepts of computer science, data mining, cognitive sciences and graphic design, this is important in controlling and measuring the quality of communication because the ability to collect, store and manage data, despite the increasing pace of its updating, remains our ability On their understanding relatively constant. The size, shape, and color of visual design elements can also play a role in communication. According to the results obtained, it was determined that the use of graphs as a visual communication tool was effective in evaluation, understanding and continuity.

A Survey on Deep Hashing Methods

Nearest neighbor search aims at obtaining the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining. Hashing is one of the most widely used methods for its computational and storage efficiency. With the development of deep learning, deep hashing methods show more advantages than traditional methods. In this survey, we detailedly investigate current deep hashing algorithms including deep supervised hashing and deep unsupervised hashing. Specifically, we categorize deep supervised hashing methods into pairwise methods, ranking-based methods, pointwise methods as well as quantization according to how measuring the similarities of the learned hash codes. Moreover, deep unsupervised hashing is categorized into similarity reconstruction-based methods, pseudo-label-based methods, and prediction-free self-supervised learning-based methods based on their semantic learning manners. We also introduce three related important topics including semi-supervised deep hashing, domain adaption deep hashing, and multi-modal deep hashing. Meanwhile, we present some commonly used public datasets and the scheme to measure the performance of deep hashing algorithms. Finally, we discuss some potential research directions in conclusion.

A study on psychological stress assessment of higher educational institution's students based on computer data mining technology.

Safety begins in the human mind, and the individual's need for psychological safety is the most fundamental need. This fundamental need takes psychological safety as the starting point for the gradual formation of a connection with the outside world. Graduates are the backbone of China's economic development, and their healthy development is of great significance to the sustainable development of China's economy and society. Excessive psychological pressure may bring pain to students in physical and psychological aspects, and even lead to suicide. If students with abnormal psychological pressure can be found in time, the school can provide help and intervention in time to relieve psychological pressure. This paper uses pressure sensor technology for data collection and data mining techniques for data analysis to assess and predict the psychological stress level of Higher Educational Institutions (HEIs) students. The results show that this method can accurately and objectively evaluate the psychological stress of the students, and the evaluation results of students' psychological stress are stable, which can provide students with psychological stress assessment services. It implies that HEI's policymakers should consider these techniques to assess the psychological stress of the students proactively.

Network Information Platform Construction Based on Computer Data Mining and Processing

Network Information Platform Construction Based on Computer Data Mining and Processing

Using Data Mining Techniques to Diagnosis of the Covid-19 Effects on the Hospital Readmission

The COVID-19 pandemic led to a substantial increase in the volume, diversity, and output pace of healthcare data. Countries depended on traditional methods to monitor diseases and public health to manage the epidemic, while advanced technology such as artificial intelligence and computation enabled efficient data processing. That datasets are usually enormous, growing exponentially, and comprise a collection of complicated item sets. To extract big, complicated itemsets, robust, straightforward, and computationally efficient techniques are crucial. Based on concepts from computer science, machine learning, and data mining, the Apriori method is a viable approach for supporting the values of database items in this study. There are two distinct implementation methods for Apiori: low confidence and support (Apiori algorithm) and the Apriori property algorithm. In conclusion, the performance of the Apriori property algorithm was superior to that of the traditional Apriori algorithm.

UIT-ADrone: A Novel Drone Dataset for Traffic Anomaly Detection

Anomaly detection plays an increasingly important role in video surveillance and is one of the issues that has attracted various communities, such as computer vision, machine learning, and data mining in recent years. Moreover, drones equipped with cameras have quickly been deployed to a wide range of applications, starting from border security applications to street monitoring systems. However, there is a notable lack of adequate drone-based datasets available to detect unusual events in the urban traffic environment, especially in roundabouts, due to the density of interaction between road users and vehicles. To promote the development of anomalous event detection with drones in the complex traffic environment, we construct a novel large-scale drone dataset to detect anomalies involving realistic roundabouts in Vietnam, covering a large variety of anomalous events. Traffic at a total of three different roundabouts in Hochiminh city was recorded from a camera-equipped drone. The resulting dataset contains 51 videos with total data traffic of nearly 6.5 hours, captured across 206K frames with ten abnormal event types. Based on this dataset, we comprehensively evaluate the current state-of-the-art algorithms and what anomaly detection can do in drone-based video surveillance. This study presents a detailed description of the proposed UIT-ADrone dataset, along with information regarding data distribution, protocols for evaluation, baseline experimental results on our dataset and other benchmark datasets, discussions, and paves the way for future work. The dataset is available online for non-commercial research at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://uit-together.github.io/datasets/UIT-ADrone/</uri> .

Mixture correntropy based robust multi-view K-means clustering

Multi-view clustering has been a significant research problem in unsupervised clustering in recent years and has important applications in computer vision, data mining and other fields. To explore more clustering information from different views and improve performance, researchers have developed a variety of multi-view clustering algorithms by applying the same L1 or L2,1 norm constraints for different views, which essentially assumes that the errors satisfy the characteristics described by the corresponding norms. It is clear that such assumption is not always satisfied in the real-world datasets. Therefore, the performance of existing algorithms can decrease under the complex noise that may be contained in the data. To solve the above problem, we introduce an information theoretic learning-based metric into a multi-view model to address noise. First, we propose a new mixture correntropy (MC) metric. Then, we propose a MC based robust multi-view K-means clustering (MC-RMVKM) method by applying the MC to an existing model. Furthermore, an efficient iterative algorithm is derived to solve the joint MC-RMVKM learning problem. Extensive results on real-world multi-view data show that the MC-based algorithm outperforms other state-of-the-art algorithms.

Sex-Specific Human, Agent, and Environment-Related Interactions in Traumatic Brain Injury: Utility of The Haddon Matrix

<h3>Research Objectives</h3> To explore sex differences in the Host, the Agent, and the Environment utilizing computational analysis of traumatic brain injury (TBI) events. <h3>Design</h3> The retrospective population-based study utilized province-wide population-based decade-long health administrative data collected through the routine operation of the publicly funded health system in Ontario, Canada. <h3>Setting</h3> We used a previously established cohort of patients discharged between the fiscal years 2007/2008 and 2015/2016 from acute care and from the emergency department (ED) with diagnoses of TBI. <h3>Participants</h3> We drew upon health records of 235,003 unique patients (57% male) with TBI and the same number of reference patients without TBI, who were individually matched based on sex, age, place of residence, and income level, to organize factors associated with the TBI event. We dissected complex and multidimensional TBI event data by exploiting data mining and information visualization methods in male and female patients separately. We adopted concepts of the Haddon Matrix (Human, Agent, Environment) to organize injury event factors and compare TBI events of male and female patients. <h3>Interventions</h3> Not applicable. <h3>Main Outcome Measures</h3> Sex differences in the health status of the Host, the Agent, and the Environment at the TBI event phase. <h3>Results</h3> Based on perceived similarities, the computational technique detected 35 injury event-related factors, allowing observation of a set of definable patterns within the Host, the Agent, and the Environment. We uncovered significant sex-based differences in Host, Agent, and Environment patterns. We found that the Host's health status is of great importance to injury severity, and the Agent and the Environment have implications for external causes of injury. <h3>Conclusions</h3> Study findings support the utility of computational data mining in examining patterns of information within the TBI event. <h3>Author(s) Disclosures</h3> Eunice Kennedy Shriver National Institute of Child Health & Human Development of the National Institutes of Health (NIH) under Award Number R21HD089106 and the National Institute Of Neurological Disorders And Stroke of the NIH under Award Number R01NS117921 and partially by Canada Research Chair Programs.

The Research and Analysis of Data Mining Technology

With the rapid development of information technology, data analysis, machine learning, artificial intelligence and other technologies arises at the historic moment, followed by the exponential growth of all kinds of information, in the current era of big data, the human brain has been unable to deal with huge amounts of daily data, which leads to the phenomenon of rich data but lack of information, thus prompted the emergence of data mining technology. Computer data mining technology has greatly improved people's quality of life, met people's material and spiritual needs, and promoted the progress and development of the society.

When Research Topic Trend Prediction Meets Fact-Based Annotations

The unprecedented growth of publications in many research domains brings the great convenience for tracing and analyzing the evolution and development of research topics. Despite the significant contributions made by existing studies, they usually extract topics from the titles of papers, instead of obtaining topics from the authoritative sessions provided by venues (e.g., AAAI, NeurIPS, and SIGMOD). To make up for the shortcoming of existing work, we develop a novel framework namely RTTP(Research Topic Trend Prediction). Specifically, the framework contains the following two components: (1) a topic alignment strategy called TAS is designed to obtain the detailed contents of research topics in each year, (2) an enhanced prediction network called EPN is designed to capture the research trend of known years for prediction. In addition, we construct two real-world datasets of specific research domains in computer science, i.e., database and data mining, computer architecture and parallel programming. The experimental results demonstrate that the problem is well solved and our solution outperforms the state-of-the-art methods.

Computational pharmacology: New avenues for COVID-19 therapeutics search and better preparedness for future pandemic crises

The COVID-19 pandemic created an unprecedented global healthcare emergency prompting the exploration of new therapeutic avenues, including drug repurposing. A large number of ongoing studies revealed pervasive issues in clinical research, such as the lack of accessible and organised data. Moreover, current shortcomings in clinical studies highlighted the need for a multi-faceted approach to tackle this health crisis. Thus, we set out to explore and develop new strategies for drug repositioning by employing computational pharmacology, data mining, systems biology, and computational chemistry to advance shared efforts in identifying key targets, affected networks, and potential pharmaceutical intervention options. Our study revealed that formulating pharmacological strategies should rely on both therapeutic targets and their networks. We showed how data mining can reveal regulatory patterns, capture novel targets, alert about side-effects, and help identify new therapeutic avenues. We also highlighted the importance of the miRNA regulatory layer and how this information could be used to monitor disease progression or devise treatment strategies. Importantly, our work bridged the interactome with the chemical compound space to better understand the complex landscape of COVID-19 drugs. Machine and deep learning allowed us to showcase limitations in current chemical libraries for COVID-19 suggesting that both in silico and experimental analyses should be combined to retrieve therapeutically valuable compounds. Based on the gathered data, we strongly advocate for taking this opportunity to establish robust practices for treating today's and future infectious diseases by preparing solid analytical frameworks.

SDNMF: Semisupervised discriminative nonnegative matrix factorization for feature learning

As one of the most effective feature learning methods, Nonnegative Matrix Factorization (NMF) has been widely used in many scientific fields, such as computer vision, data mining, and bioinformatics. However, NMF is an unsupervised method that cannot fully utilize the label information of data. Thus, its performance is limited in some recognition and classification problems. To remedy this shortcoming, this paper proposes a Semisupervised Discriminative NMF (SDNMF) method. First, we design a Soft-Labeled NMF (SLNMF) model by introducing a soft-label matrix-based regression term into the original NMF, so that the relationship between the soft-label matrix and low-dimensional features can be constructed to improve the discriminative ability of low-dimensional features. Second, to effectively estimate the soft-label matrix, a Label Propagation (LP) model is adopted to fully explore the spatial distribution relationship between the labeled and unlabeled samples. Third, an Adaptive Graph Learning (AGL) model is proposed to exploit the geometric relationship of samples well, which could enhance the performance of LP. Finally, the above three models (i.e., SLNMF, LP, and AGL) are integrated into a unified framework for effective feature learning, which can not only effectively explore the structural relationship matrix between data, but also predict the labels for unknown samples. Moreover, an iterative optimization algorithm is presented to solve our objective function. The convergence and computational complexity analysis of the proposed SDNMF method are also provided. Extensive experiments are conducted on several standard data sets. Compared with related methods, the experimental results verify that the proposed SDNMF method achieves better performance.

Research on Mining Balanced Competition Strategy in Financial Market Based on Computer Data Mining Method

The mining process of traditional market equilibrium competition strategy is difficult to deal with massive data, resulting in the inability to accurately classify customer data in the process of competition strategy customization. Therefore, this paper proposes a strategy formulation method of balanced competition in the financial market based on computer data mining. Firstly, the process of the k-means clustering algorithm was optimized, and Murkowski distance and Markov distance were used as classification basis to find some potential information hidden in the data. Based on the optimized K-means clustering algorithm for data processing, in order to achieve effective data analysis, design customer behavior data mining process and analyze customer value matrix and customer pyramid. Finally, the layout framework of a balanced competition strategy in the financial market is established. The results show that the classification accuracy of the design method is higher than that of the traditional method in different states.

Active components and molecular mechanism of Syringa oblata Lindl. in the treatment of endometritis based on pharmacology network prediction.

Antibiotic treatment of endometritis was limited by the inevitable antibiotic residues and risk of bacterial resistance. Therefore, the development of safe and effective strategies for endometritis treatment is urgently needed. Syringa oblata Lindl. (SOL) showed great pharmacological potential against endometritis. However, the active components and underlying mechanism of SOL for endometritis treatment remain indeterminate. In our study, the active components and possible molecular mechanism of SOL against endometritis were predicted through computer data mining and biological networks construction. It was predicted that the main active components of SOL were luteolin, kaempferol, oleanolic acid, and rutin, and their anti-endometritis effect was mainly attributed to the TLRs/NF-κB signaling pathway. Furthermore, a green and efficient deep eutectic solvent combined with ultrasound-assisted extraction (DES-UAE) was performed and optimized to obtain high contents of total flavonoid, rutin, and luteolin. The four predicted active components in the SOL extracts were qualitatively and quantitatively analyzed by LC/MS and HPLC. Finally, the pharmacological effects of SOL and active components have been verified by Staphylococcus aureus-endometritis models in mice. H&E staining and bacterial load in uterus tissues assays initially validated the pharmacodynamic effects of SOL, and quantitative real-time PCR (RT-qPCR) and ELISA results confirmed that SOL and four active components could ameliorate the uterus injury caused by Staphylococcus aureus, the mechanism of action is related to the TLRs/NF-κB signaling pathway.

Data Mining Technology for Agricultural Equipment Machinery and Information Network Data Resources

In order to realize the automation and intelligence of agricultural equipment mechanical state detection and improve the efficiency and accuracy of agricultural machinery equipment detection technology, this paper proposes an intelligent agricultural machinery equipment state detection method based on computer data mining. This method uses support vector machine to classify the equipment status and uses ant colony algorithm to solve the optimization problem. Its basic logic is to collect the status data of agricultural machinery equipment, extract the status detection characteristics of agricultural machinery equipment, and use computer data mining to establish an automatic state detection model of agricultural machinery equipment. The application results show that the correct rate of the state detection of agricultural machinery equipment is more than 95%, and the false detection rate of the state of agricultural machinery equipment is far lower than that of other current state detection methods of agricultural machinery equipment. Conclusion. This method can realize high-precision real-time detection of agricultural machinery equipment and has higher practical value.

An Audit Risk Model Based on Improved BP Neural Network Data Mining Algorithm

Professional auditors provide audit services to businesses and they are key participants in enterprise development. Effective identification of audit risks can help auditors plan their audit work rationally and issue correct audit opinions. In the era of big data and the Internet, enterprises generate a large amount of data in their daily operations. For auditors, it is a great challenge to use data mining algorithms, machine learning, artificial intelligence, and other emerging technologies to identify high-quality audit data from the vast amount of data of audited enterprises. At the same time, some companies may falsify and modify their financial statements for their own benefit, which further increases the difficulty for auditors in conducting audits. Traditional auditing methods are costly and consuming and cannot meet standard auditing requirements. Therefore, this study applies computer data mining algorithms to construct an audit risk model that provides a reference for auditors to conduct big data analysis and mines valuable data, thereby improving the efficiency and accuracy of the audit process.

Application of Mirror Materials in Wood Furniture Manufacturing Process Based on Big Data Analysis

With the development of the national economy, the interior decoration work has received extensive attention, and the traditional decoration methods have been unable to meet its actual work needs. The application of mirror materials in interior decoration can not only enrich the technical methods of interior decoration, but also improve the decoration quality and comfort, so as to meet people’s growing decoration needs, achieving the purpose of promoting the sound development of interior decoration. Mirror material is one of the decorative materials widely used in modern indoor environment. It not only has decoration, but also can expand space. In recent years, the advent of the era of big data has promoted the reform of the design industry. Using big data thinking to assist the innovative design of furniture products will also become an important trend in the development of the furniture industry. According to the characteristics of customer demand in the era of big data, this paper designs and develops a set of customer demand analysis system based on big data by using cloud computing and big data mining technology. By collecting the behavior data of users when using products, this paper combines the mirror material with the manufacturing process of wooden furniture. The mining algorithm is applied to find out the improvement goal and direction of wood furniture manufacturing process based on mirror material, so as to enhance the competitiveness of furniture enterprises. The method proposed in this paper can obtain the furniture design elements according to the functional zoning and theme information and input the furniture design elements and zoning elements into the design element matching evaluation model to obtain the design matching element information.

Development of Employer Brand Evaluation Scale Based on Computer Data Mining and Its Relationship with College Students’ Job-Hunting Intention

The inclinations among employees are changed because of the evolutions in the twenty-first century’s workplace. It is consequently critical to decide the elements that workers look for in an organization and their goal conduct to stop from their occupation to work on the issues of high wearing down that occurs in an organization. This study determines the connection between employer branding and turnover intention among employees. Data mining and factor analysis methods are used to extract public factors, design a more concise employer brand evaluation system, and develop a new employer brand evaluation scale. The relationship between the various dimensions of employer brand in China’s banking industry and college students’ job-hunting intentions are examined. Results show that contemporary college student job-seekers in China pay more attention to short-term and directly experienced security and experiential needs. It ignores the long-term and hard-to-feel self-realization needs and respect needs in the short term. These dimensions reflect the perceptions of existing employees regarding their organization. The scale is found to be statistically sound for measuring the employer brand.

Road Condition Monitoring Using Smart Sensing and Artificial Intelligence: A Review.

Road condition monitoring (RCM) has been a demanding strategic research area in maintaining a large network of transport infrastructures. With advancements in computer vision and data mining techniques along with high computing resources, several innovative pavement distress evaluation systems have been developed in recent years. The majority of these technologies employ next-generation distributed sensors and vision-based artificial intelligence (AI) methodologies to evaluate, classify and localize pavement distresses using the measured data. This paper presents an exhaustive and systematic literature review of these technologies in RCM that have been published from 2017–2022 by utilizing next-generation sensors, including contact and noncontact measurements. The various methodologies and innovative contributions of the existing literature reviewed in this paper, together with their limitations, promise a futuristic insight for researchers and transport infrastructure owners. The decisive role played by smart sensors and data acquisition platforms, such as smartphones, drones, vehicles integrated with non-intrusive sensors, such as RGB, and thermal cameras, lasers and GPR sensors in the performance of the system are also highlighted. In addition to sensing, a discussion on the prevalent challenges in the development of AI technologies as well as potential areas for further exploration paves the way for an all-inclusive and well-directed futuristic research on RCM.

Metabolomics-based phenotypic screens for evaluation of drug synergy via direct-infusion mass spectrometry

SummaryDrugs used in combination can synergize to increase efficacy, decrease toxicity, and prevent drug resistance. While conventional high-throughput screens that rely on univariate data are incredibly valuable to identify promising drug candidates, phenotypic screening methodologies could be beneficial to provide deep insight into the molecular response of drug combination with a likelihood of improved clinical outcomes. We developed a high-content metabolomics drug screening platform using stable isotope-tracer direct-infusion mass spectrometry that informs an algorithm to determine synergy from multivariate phenomics data. Using a cancer drug library, we validated the drug screening, integrating isotope-enriched metabolomics data and computational data mining, on a panel of prostate cell lines and verified the synergy between CB-839 and docetaxel both in vitro (three-dimensional model) and in vivo. The proposed unbiased metabolomics screening platform can be used to rapidly generate phenotype-informed datasets and quantify synergy for combinatorial drug discovery.