Multidimensional Data Analysis Research Articles

An MBD-driven order remaining completion time prediction method based on SSA-BiLSTM in the IoT-enabled manufacturing workshop

The transformation of production mode leads to the need to strictly ensure the order in-time delivery. The global control ability of manufacturing workshops has become a necessary capability for enterprises. The real-time accurate Order Remaining Completion Time (ORCT) prediction allows managers to master the production schedule fluctuation, which provides criteria for workshop management. Due to the widespread deployment of Internet of Things (IoT) devices in the workshop, the difficulty of systematic processing and analysis of multi-dimensional heterogeneous data has been the main pain point of ORCT prediction. To tackle these problems, a Manufacturing Big Data (MBD)-driven ORCT prediction method based on Salp Swarm Algorithm (SSA) and Bidirectional Long Short-Term Memory (BiLSTM) is proposed. An attribute selection algorithm combined with max-relevance and min-redundancy and regularisation is used to mine key data from MBD. An SSA-BiLSTM model is proposed to achieve efficient and accurate ORCT prediction. The prediction model is supported by BiLSTM, and the hyperparameters are optimised by SSA. Finally, a case study about ORCT prediction in the IoT-enabled manufacturing workshop is presented. The result verifies that the proposed ORCT prediction method has obvious advantages over the other three traditional methods in accuracy and efficiency.

Study and analysis of wastewater treatment in the refining and chemical industry based on multidimensional data analysis

Abstract To improve the efficiency of wastewater treatment in the refining chemical industry, this paper designs a wastewater treatment process in the refining chemical industry based on multidimensional data analysis to guarantee the optimal operation of wastewater treatment operations. In the process of multidimensional data analysis, triangular polynomials are introduced to calculate the robust distance of high-dimensional data and construct a multidimensional data model. The optimal multidimensional clustering levels are divided using data operations to obtain high-dimensional data sequences in the multidimensional data set to accelerate data clustering. A parallel coordinate system realizes the visual representation of the wastewater treatment process stems to improve the capacity representation of wastewater treatment data. Simulation analysis was conducted to verify the treatment effect of the wastewater treatment process based on multidimensional data analysis in the refining and chemical industries. The results showed that the process designed in this paper resulted in a dissolved organic matter fraction concentration of 16.28, and the humic acid-like fraction increased by 36.2%, which was significantly higher than the protein-like fraction of 21.6%. And among all protein-like fractions, only C4 was positively and significantly correlated with fluorescent organic matter at the P < 0.05 level. It can be seen that the multidimensional data analysis model is conducive to promoting the development of wastewater treatment technology in the refining chemical industry and ensuring that the refining chemical industry steps into a circular and sustainable development track.

Fully nondestructive analysis of capsaicinoids electrochemistry data with deep neural network enables portable system.

Electrochemical methods have been extensively applied for the detection of chemical information from food or other analytes. However, existing electrochemical methods are limited to focusing solely on the absorption peaks and disregard much of the hidden chemical fingerprint information. Consequently, electrochemical sensors are constrained by their ability to detect samples containing multiple source-material mixtures with overlapping constituents. We hypothesized that the target substances can be effectively identified and detected using differential sensor data combined with artificial intelligence (AI). In this study, we developed a novel signal array composed of five metal electrodes and used a convolutional neural network (CNN) model for feature extraction to detect capsaicinoids in stews. Our results indicate that the proposed method achieved satisfactory predictions with a root mean square error (RMSE) of 5.407 in independent brine samples. This provides a promising strategy and practical approach for the nondestructive analysis of multidimensional electrochemical data of mixed analytes.

Mechanical properties and microscopic characteristics of steel fiber coal gangue concrete

Incorporation of coal gangue in the concrete mixes can realize utilization of the solid waste and reduce extraction/use of natural aggregates. To improve the mechanical properties of coal gangue concrete, this paper studies use of steel fibre together with coal gangue coarse aggregate, coal gangue fine aggregate/sand in various concrete mixes. The effect of volume dosages of steel fibre and different levels of replacing nature coarse aggregate and river sand with coal gangue aggregates on concrete compressive strength was first investigated. Then, a design of experiment using orthogonal test was adopted to study concrete mixes with 3 factors, namely, coal gangue coarse aggregate, coal gangue sand and steel fibre, and each at 3 levels. Through multidimensional statistical data analysis of the test results, the primary and secondary factors and the optimal composition of the steel fibre reinforced coal gangue concrete were identified, and a grey prediction model for compressive strength of the concrete mixes established. The microstructural characteristics and failure mechanism of steel fiber reinforced coal gangue concrete was also studied and discussed.

Physical Activity Pattern of Adults With Metabolic Syndrome Risk Factors: Time-Series Cluster Analysis.

Physical activity plays a crucial role in maintaining a healthy lifestyle, and wrist-worn wearables, such as smartwatches and smart bands, have become popular tools for measuring activity levels in daily life. However, studies on physical activity using wearable devices have limitations; for example, these studies often rely on a single device model or use improper clustering methods to analyze the wearable data that are extracted from wearable devices. This study aimed to identify methods suitable for analyzing wearable data and determining daily physical activity patterns. This study also explored the association between these physical activity patterns and health risk factors. People aged >30 years who had metabolic syndrome risk factors and were using their own wrist-worn devices were included in this study. We collected personal health data through a web-based survey and measured physical activity levels using wrist-worn wearables over the course of 1 week. The Time-Series Anytime Density Peak (TADPole) clustering method, which is a novel time-series method proposed recently, was used to identify the physical activity patterns of study participants. Additionally, we defined physical activity pattern groups based on the similarity of physical activity patterns between weekdays and weekends. We used the χ2 or Fisher exact test for categorical variables and the 2-tailed t test for numerical variables to find significant differences between physical activity pattern groups. Logistic regression models were used to analyze the relationship between activity patterns and health risk factors. A total of 47 participants were included in the analysis, generating a total of 329 person-days of data. We identified 2 different types of physical activity patterns (early bird pattern and night owl pattern) for weekdays and weekends. The physical activity levels of early birds were less than that of night owls on both weekdays and weekends. Additionally, participants were categorized into stable and shifting groups based on the similarity of physical activity patterns between weekdays and weekends. The physical activity pattern groups showed significant differences depending on age (P=.004) and daily energy expenditure (P<.001 for weekdays; P=.003 for weekends). Logistic regression analysis revealed a significant association between older age (≥40 y) and shifting physical activity patterns (odds ratio 8.68, 95% CI 1.95-48.85; P=.007). This study overcomes the limitations of previous studies by using various models of wrist-worn wearables and a novel time-series clustering method. Our findings suggested that age significantly influenced physical activity patterns. It also suggests a potential role of the TADPole clustering method in the analysis of large and multidimensional data, such as wearable data.

Analysis of the effects of physical activity on chronic diseases based on multidimensional data analysis

Abstract In recent years, the incidence of chronic diseases in the middle-aged and elderly population has been increasing, with high morbidity, disability, and mortality rates, and is one of the most dangerous factors leading to death in middle-aged and elderly people. Although drugs are the most common means of treating chronic diseases, long-term medication can bring serious side effects and cause chronic damage to multiple organs. Evidence-based medical evidence shows that sports prescription interventions have better intervention effects on chronic diseases without side effects, and they have become a common means to promote recovery and improve the quality of life of patients with chronic diseases. In this paper, we will analyze the effects of different sports on the indicators of chronic diseases from a multidimensional perspective and develop a scientific sports prescription to help patients with chronic diseases recover. The experimental results show that high-intensity intermittent exercise and resistance exercise also have good intervention effects on patients with chronic diseases; in addition, different exercise prescription factors such as exercise intensity, exercise time, and exercise items directly affect the intervention effects of exercise, and unscientific exercise prescriptions not only fail to promote patients’ recovery but also bring adverse effects on patients’ physical functions and even aggravate the development of the disease. The recovery of the physical function of the patients in the experimental group is sufficient to show the feasibility of exercise intervention. Therefore, the development of scientific exercise intervention prescriptions is of great significance to the rehabilitation of patients with chronic diseases.

Preferable academic work forms of medical students in the era of digitalization

The article presents the sociological study results on the preferred forms of medical students’ academic work in the era of digitalization. The study was carried out among students of the Volga Research Medical University using an online survey. The study purpose is to identify the attitude of various typological groups of medical students to various forms and methods of scientific and methodological support of the educational process, including the use of digital technologies. The work showed that behind the variety of medical students’ attitudes on the effectiveness of different forms of education, there is a willingness of young people to move away from traditional methods of obtaining professional knowledge and skills, and they clearly have a complex request for new forms of teaching, including using the Internet and electronic resources. The assessment of various forms and teaching methods has noticeable differences depending on the affiliation of students to various faculties. The article analyzes the students’ assessments of the various forms’ effectiveness of education using multidimensional data analysis, which made it possible to identify four types of student attitudes: 1) orientation to online learning; 2) live contact with the teacher; 3) electronic library; 4) work with summaries of educational materials. Each of these types contains its own set of preferred and rejected items

Evaluation of the Possible Pathways Involved in the Protective Effects of Quercetin, Naringenin, and Rutin at the Gene, Protein and miRNA Levels Using In-Silico Multidimensional Data Analysis.

Flavonoids are secondary metabolites that are non-essential for plant growth or survival, and they also provide numerous health benefits to humans. They are antioxidants that shield plants from the ill effects of ultraviolet light, pests, and diseases. They are beneficial to health for several reasons, including lowering inflammation, boosting cardiovascular health, and lowering cancer risk. This study looked into the physicochemical features of these substances to determine the potential pharmacological pathways involved in their protective actions. Potential targets responsible for the protective effects of quercetin, naringenin, and rutin were identified with SwissADME. The associated biological processes and protein-protein networks were analyzed by using the GeneMANIA, Metascape, and STRING servers. All the flavonoids were predicted to be orally bioavailable, with more than 90% targets as enzymes, including kinases and lyases, and with common targets such as NOS2, CASP3, CASP9, CAT, BCL2, TNF, and HMOX1. TNF was shown to be a major target in over 250 interactions. To extract the "biological meanings" from the MCODE networks' constituent parts, a GO enrichment analysis was performed on each one. The most important transcription factors in gene regulation were RELA, NFKB1, PPARG, and SP1. Treatment with quercetin, naringenin, or rutin increased the expression and interaction of the microRNAs' hsa-miR-34a-5p, hsa-miR-30b-5p, hsa-let-7a-5p, and hsa-miR-26a-1-3p. The anticancer effects of hsa-miR-34a-5p have been experimentally confirmed. It also plays a critical role in controlling other cancer-related processes such as cell proliferation, apoptosis, EMT, and metastasis. This study's findings might lead to a deeper comprehension of the mechanisms responsible for flavonoids' protective effects and could present new avenues for exploration.

Shenzhen – A typical benchmark of Chinese rapid urbanization miracle

Shenzhen is one of the world's cities with the fastest urbanization and the most astonishing changes, and it is also a typical benchmark of Chinese rapid urbanization miracle. Under the tide of neoliberalism and globalization, the central government gave Shenzhen the priority of reform and experimentation first, then it has been rapidly pushed to the front stage as a test field for China's reform and opening up. Shenzhen has become the world's first-tier city in a short time with its location advantage and high-quality talent attraction, as well as active private economy and scientific and technological innovation. Through the multi-dimensional data analysis of the great changes during Shenzhen's urbanization, and a summary of the advantages of the Shenzhen model, this paper systematically answers the question that why Shenzhen can achieve urbanization so quickly. Furthermore, it concludes challenges of Shenzhen's future development and discusses the inspirations of the Shenzhen model for other cities. Based on the above analysis, this paper constructs an organic framework comprehensively covering achievements, characteristics, challenges, and inspirations of Shenzhen's rapid urbanization model. In the future, Shenzhen needs to transform from “Shenzhen Speed” to “Shenzhen Quality” to realize sustainable high-quality urbanization.

Employment of relaxation times distribution with improved elastic net regularization for advanced impedance data analysis of a lithium-ion battery

Electrochemical impedance spectroscopy (EIS) is a familiar conventional approach that has been widely applied to analyze electrochemical systems, such as batteries and fuel cells, to determine the polarization resistances of their electrodes. An improved method that can effectively interpret EIS spectra with high resolution and provide close knowledge of the time features of the electrochemical system being considered is the distribution of relaxation times (DRT). However, estimating and attaining DRT is a challenging issue that involves solutions being obtained by employing regularization techniques. This study proposed an improved elastic net (IEN) regularization with an adaptive elastic net penalty, wherein adaptive weight matrices were incorporated into the elastic net penalty. The proposed technique was first validated on standard artificial experimental elements: RC circuit, fractal-RC (FRC) circuit, ZARC element, and Gerischer element, each with a known analytical DRT. The results showed that the proposed method exhibited better estimation accuracy in obtaining the exact known DRTs and resistances, and lower mean square errors (MSEs) when compared with the conventional elastic net (EN) regularization method. Furthermore, the proposed method was applied to the EIS data of real lithium-ion batteries with different state-of-charge (SOC) and temperatures, where the obtained DRTs provided an intuitive analysis of the processes within the battery. The proposed model can accurately estimate various time characterizations and identify their processes. Besides the DRTtool results are correspondingly similar to this study's results showing the effectiveness of the proposed approach when compared. However, the limitations and weaknesses of the proposed approach were recognized and reported in this study. Moreover, the proposed approach can be further extended, improved, and employed for advanced EIS techniques and multidimensional EIS data analyses.

STRATEGIC COMPETENCE AS A GUARANTEE OF PROFESSIONAL ACTIVITY OF A MODERN IT SPECIALIST

The article examines the current problem of professional training of future IT specialists in the context of forming their strategic competence because it is critical for university graduates in the field of IT to be able to strategically plan actions in different ways for effective implementation in their professional activities. Therefore, the strategy of professional activity is carried out by means of separate tactical actions, which collectively make up strategic activity. Thus, s IT specialists’ shaping strategic competence allows understanding of which actions are the most important for the realization of the goal and the achievement of professional tasks. It has been established that strategic competence of an IT specialist is a personal integrative creation. This represents the unity of professionally significant qualities, knowledge and skills, with the help of which specialists formulate the strategic goal of work, show a value-motivational attitude to strategic changes and flexibility in behaviour depending on the factors of the external environment, make a reasonable choice and implement strategies depending on the situation, while achieving the effectiveness of the professional activity. The importance of shaping strategic competence in three main sections is substantiated including: elemental (a set of components, the interaction between which ensures the implementation of the relevant activity); functional (methodology for adopting strategies); and procedural (technology for developing and implementing a strategy in the existing environment). It has been proved that a high level of IT specialists’ strategic competence ensures the following: determination of the leading goal of professional activity, choosing an effective model of professional behaviour following existing conditions, planning and development of measures for adaptation to conditions of professional activity, implementation of planned professional actions and operations (strategies), etc. The article also presents the main aspects of professional training of future IT specialists. The experience of organizing and implementing university training for future IT specialists shows that a high level of strategic competence makes it possible to choose and prepare the right hardware and software, rational methods for solving professional tasks, allows for the modernization of IT infrastructure, optimization of IT efficiency for innovation. This makes it possible to manage the IT sector, in particular, in the context of IT infrastructure management, IT projects, IT costs, to increase the security and stability of the industry. It is important to define long-term goals, taking into account the phased process of optimizing existing IT systems. A strong emphasis is also placed on the following blocks of scientific knowledge: the use of technologies and algorithms of computational intelligence and intelligent data analysis in the tasks of forecasting, analytics, cluster analysis using software tools to support multidimensional data analysis based on DataMining, TextMining, WebMining technologies, mastering system programming languages and methods of developing online programs, performing parallel and distributed calculations, applying numerical methods and algorithms, etc. The article also provides promising directions for research as a study of the real state of shaping strategic competence of future bachelors in the IT field.

The impact of supply chain management on a company's operation and decision based on the multidimensional data analysis of upstream and downstream industry market states.

This study provides data analysis support for the entire enterprise procurement management process, thereby improving the management effectiveness of supply chain operations. It analyzes upstream and downstream industry market status data in the supply chain and various primary data in enterprise management activities. By utilizing the Delphi method to screen and verify multimode market status data indicators, which significantly impact upstream and downstream industries in multiple rounds, 28 types of market status data were selected for analysis. This analysis aimed to investigate the effect of supply chain management on operational decisions within the company. The data reduction method based on adaptive statistics was the most effective in revealing the market status and promoting efficient operation decision-making based on supply chain management. This study also suggests a brand-new technique for measuring supply chain performance based on the Levenberg-Marquardt Back Propagation (LMBP) algorithm, offering a more impartial manner of doing so. The performance evaluation results showed a maximum error level of less than 0.4% when paired with empirical analysis. The proposed optimization model provides strategic guidance for optimizing supply chain management and improving overall performance.

ECG-Based Stress Detection and Productivity Factors Monitoring: The Real-Time Production Factory System

Productivity and production quality have become primary goals for the success of companies in all industrial and manufacturing sectors. Performance in terms of productivity is influenced by several factors including machinery efficiency, work environment and safety conditions, production processes organization, and aspects related to workers’ behavior (human factors). In particular, work-related stress is among the human factors that are most impactful and difficult to capture. Thus, optimizing productivity and quality in an effective way requires considering all these factors simultaneously. The proposed system aims to detect workers’ stress and fatigue in real time using wearable sensors and machine learning techniques and also integrate all data regarding the monitoring of production processes and the work environment into a single platform. This allows comprehensive multidimensional data analysis and correlation research, enabling organizations to improve productivity through appropriate work environments and sustainable processes for workers. The on-field trial demonstrated the technical and operational feasibility of the system, its high degree of usability, and the ability to detect stress from ECG signals exploiting a 1D Convolutional Neural Network (accuracy 88.4%, F1-score 0.90).

Assessing primary vegetation recovery from earthquake-induced landslide scars: A real-time kinematic unmanned aerial vehicle approach

Globally, post-disturbance site formation is caused by large-scale natural disturbances. In such areas, it is necessary to restore vegetation rapidly as it regulates the outflow of sediment and water. However, the relationship between post-disturbance site vegetation recovery and environmental factors has not yet been elucidated. This study aimed to estimate the environmental factors affecting early vegetation recovery after large-scale disturbances (i.e., earthquakes). We used a novel analysis of multidimensional high-definition earth surface data derived from real-time kinematic unmanned aerial vehicles (RTK-UAVs) with high positioning accuracy to reveal primary vegetation recovery conditions, accounting for ground surface changes and environmental information of earthquake-induced landslide scars in Japan's boreal forests. A vegetation survey was conducted to understand the species composition and coverage that had recovered from earthquake-induced landslide scar in Japan's boreal forests. The herbaceous species Petasites japonicus subsp. giganteus and the woody introduced species Larix kaempferi were identified as the dominant species that help restore vegetation, with high frequency and plant coverage in the primary succession of the landslide scar. The reproductive characteristics of these pioneer species suggest that they have an advantage for establishment and growth, particularly on landslide scars with substantial topsoil dynamics. An optimal generalized linear model was used, which considered the distance from the vegetation inside and outside the landslide scars, ground surface change, inclination angle, annual amount of solar radiation, and the local region as explanatory variables. The ideal environmental conditions for vegetation recovery are summarized as follows: 1) Maximum biological legacy preserved inside and outside landslide scars. 2) Vegetation recovery expected in stable areas with little erosion and accumulation. 3) Vegetation recovery expected on slopes other than steep slopes or those with extremely high amounts of sunlight. The vegetation recovery conditions and RTK-UAV remote-sensing techniques used in this study can be applied to vegetation restoration zoning plans immediately after a disaster in similar environments.

Abstract 91: Unsupervised Machine Learning Predicts Invasive and Undruggable Long Coding Rna Linc00662, Linc01234, and Spanxa1, Rabphilin 3a, Svil Antisense Rna 1 Like From Oral Cancer Transcriptomics

Abstract Purpose: Numerous cancer disease-modifying targets look “undruggable” or “difficult to target” because they lack accessible deep hydrophobic pockets where small molecules can bind, or they lack enzymatic activity (have no active site), RAS, and transcription factors (STAT3, TP53, MYC) are archetypal cancer undruggable. Designing a small molecule to bind to a PPI interface has proven difficult for several reasons. First, the unique interface structure is a challenge for drug design. Compared with the binding pockets of conventional protein targets, the interface of PPIs tends to be flat and contains few pockets, making it difficult for small-molecule compounds to bind. Designing a tiny chemical to bind to a PPI interface is tricky. First, the unusual interface structure presents a hurdle for drug design: the PPI interface is flat compared to traditional protein targets. It includes few pockets, making it challenging for small-molecule drugs to attach. Although initiatives to regulate RNA and protein expression with small molecules, biological compounds, such as anti-sense technology, have remained the most often deployed approach to target disease-associated RNAs. This study aims at predicting undruggable long coding RNA and transcription factors using unsupervised analysis from oral cancer transcriptomics. Methods: Using the NCBI geo database, GSE160395 data was retrieved for unsupervised analysis. PCA(Principal Component Analysis), T SNE (t-Distributed Stochastic Neighbor Embedding and MDS analysis of multi-dimensional data were analyzed for multi-dimensional data. Using the GEO2R online analysis tool (http://www.ncbi.nlm.nih.gov/geo/geo2r), the DEGs between HSC-3 and HSC-3-M3 cell lines samples were analyzed. DEGs with a threshold criterion of 1:0 log fold change and a P value of 0.05 were considered significantly differentially expressed. Results: Top differential genes include LINC00662, MYEOV, LGALS7, MAGED1, NT5M, AKR1C1, RPH3AL, LINC01234, KRT31, SPANXA1, SVIL ANTI-SENSE RNA 1.Clustering is an unsupervised machine learning technique that is effective at finding hidden groups in data. Targeting non-coding RNA and less hydrophobic proteins is crucial for cancer prevention and metastasis. By controlling the Wnt/-catenin pathway, LINC00662 and SVIL ANTISENSE RNA 1 can facilitate and hasten the formation of OSCC. Conclusion: Anti-sense technology and proteolysis-targeting chimeras will help solve complex biological undruggable proteins. Citation Format: Pradeep Kumar Yadalam, Raghavendra Vamsi Anegundi, Ramya Ramadoss. Unsupervised Machine Learning Predicts Invasive and Undruggable Long Coding Rna Linc00662, Linc01234, and Spanxa1, Rabphilin 3a, Svil Antisense Rna 1 Like From Oral Cancer Transcriptomics [abstract]. In: Proceedings of the 11th Annual Symposium on Global Cancer Research; Closing the Research-to-Implementation Gap; 2023 Apr 4-6. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2023;32(6_Suppl):Abstract nr 91.

Improved multivariate multiscale sample entropy and its application in multi-channel data.

Entropy, as a nonlinear feature in information science, has drawn much attention for time series analysis. Entropy features have been used to measure the complexity behavior of time series. However, traditional entropy methods mainly focus on one-dimensional time series originating from single-channel transducers and are incapable of handling the multidimensional time series from multi-channel transducers. Previously, the multivariate multiscale sample entropy (MMSE) algorithm was introduced for multi-channel data analysis. Although MMSE generalizes multiscale sample entropy and provides a new method for multidimensional data analysis, it lacks necessary theoretical support and has shortcomings, such as missing cross-channel correlation information and having biased estimation results. This paper proposes an improved multivariate multiscale sample entropy (IMMSE) algorithm to overcome these shortcomings. This paper highlights the existing shortcomings in MMSE under the generalized algorithm. The rationality of IMMSE is theoretically proven using probability theory. Simulations and real-world data analysis have shown that IMMSE is capable of effectively extracting cross-channel correlation information and demonstrating robustness in practical applications. Moreover, it provides theoretical support for generalizing single-channel entropy methods to multi-channel situations.

Feature Analysis in High-Dimensional Data: Structure-Activity Relationships of Lewis Acid-Transition-Metal Complex-Catalyzed H2 Activation.

Lewis acid-transition metal (LA-TM) catalysts have been proven to have an advantage in catalyzing hydrogen activation. Herein, a high-dimensional structure-activity relationship study is performed for LA-TM-catalyzed hydrogen activation by density functional theory calculations. The DPB-Ni complex is taken as the representative catalyst, and the explored Lewis acid sites and transition-metal centers include B, Al, Ga and Ni, Pd, Pt, respectively. Totally, four general hydrogen activation mechanisms are systematically studied among the nine catalytic systems. The Ga-Ni system undergoes the lowest free energy of activation (11.0 kcal/mol), which is considered to be the optimal combination of the Lewis acid site and transition-metal center. Furthermore, more than 100 parameters are used to analyze the structure-activity relationship, including the physical structure, the bond order, the atom charge, and many other properties. Key parameters of important structures are dug out to show a high correlation with the activity of the LA-TM systems, including the M-H2 distance, the H-H bond length, the second-order perturbation stabilization energy of M-H2, the bond order of the LA-TM, and so on. The multivariable analysis indicates that the feature related to the basic elemental properties and the global feature codetermine the activity of the catalyst. In the LA-TM system, the combination of IpLA/IpTM (Ip, the first ionization energy, the feature related to basic elemental properties) and the chemical hardness (the global feature) can better explain the activity of the catalyst. The IpLA/IpTM reflects the difficulty of breaking the LA-TM bond, affecting the reaction site of activating hydrogen. The hardness reflects the stability and reactivity of LA-TM-RC complexes. The above two features with the addition of the LA-TM bond length (the local feature) can better reflect the activity of the LA-TM system-catalyzed H2 activation. The feature combinations and the method of multidimensional data analysis should be informative guidance for the rational design of efficient LA-TM catalysts for H2 activation.

Research on education management system based on machine learning and multidimensional data modeling

Abstract With the rapid development of modern information technology, especially the continuous improvement of computer network technology, the application of education management system in teaching is becoming more and more extensive. Therefore, education management system and machine learning will become an important combination direction of education. First, design and implement a complete network education management system based on B/S architecture, and design from the overall system design, detailed design and database design. Among them, the computer language combined with the SQL Server database realizes the network teaching function and the education system management function. Then, PSO-SVM machine learning is adopted to make personalized learning course recommendation for students. Multi-dimensional data analysis and feature extraction. Finally, the PSO-SVM proposed in this paper is applied to the education management system for modeling training, and compared with other traditional machine learning personalized recommendation accuracy and likeness of learning course recommendation. The experimental results show that the PSO-SVM proposed in this paper is superior to other traditional machine learning models in terms of personalized learning course recommendation and favorability, with an accuracy rate of 94.7%.

A fast retrieval method of drug information based on multidimensional data analysis

A fast retrieval method of drug information based on multidimensional data analysis

HyperCube4x: Exploring and Analyzing Data in Virtual Reality Using HyperRelational and HyperAnalyzer

Hypercube is a novel viewport management and information visualization system proposal that introduces three applications (called WorkScenes), focusing on interaction, immersive reading, data exploration, analysis, and visualization concepts. After presenting the conceptual description, interaction metaphors, and the prototype in a previous publication, this article presents HyperRelational and HyperAnalyzer, the WorkScenes focused on multidimensional data exploration, analysis, and visualization. First, the manuscript explores previous work on Human-Computer Interaction-related disciplines, such as cognitive psychology, cognitive engineering, and neuroscience. Then, we introduce HyperRelational and HyperAnalyzer, focusing on their fundamental concepts 1) Geometrical visualization; 2) mapping relationships among information as spatial dimensions. Also, the Screenshots help illustrate the mentioned concepts. Finally, the “Results and Discussion” section demonstrates how these features integrate with the flow, presence, and immersion of Virtual Reality, fit Shneiderman’s visual-information-seeking mantra and solve some desktop metaphor-related issues. Additionally, we present test results conducted with 26 participants that show an acceptability rate of 74% amongst users and highlight their positive feedback/experience regarding HyperAnalyzer. On the other hand, the System Usability Scale (SUS) evaluation scored 60.6731. The score demonstrates that HyperAnalyser scored a little better than Microsoft Excel. Therefore, we conclude that the concepts presented here are viable, but it is still necessary to evolve usability to make HyperCube commercially viable.