Tactical optimisation and opponent analysis for football teams with big data mining and machine learning

Football tactical training is of great significance to the improvement of football level and the development of football, while the tactical training system is rich in content and diversified in structure, how to coordinate the content of tactical trainingsystem has become a key topic to improve the effectiveness of tactical training. In this paper, we design the method of tactical training for college football teams, aiming at building a tactical optimisation and opponent analysis model based on big data mining and machine learning from the reality of tactical training for college high-level football teams. Specifically, the convolutional neural network with two levels of cascade detection and regression in the model adopts the classic ideas of face key point detection and human body key point detection: the idea of cascade regression is used for the detection of the key point location from coarse to fine; the heat map of the key point obtained from the first level network is used as the supplemental information, and the original map is used for the feature fusion; the Heatmap, which has better effect, is used as the Ground Truth of the network; the Heatmap is used as the ground truth of the network; the Heatmap, which has better effect, is used as the ground truth of the network. The second stage regression network uses Heatmap as the Ground Truth of the network, which provides pixel-by-pixel supervision for the regression of the key points' positions and the prediction of whether the key pointsare visible ornot. In addition, this paper combines the idea of adversarial learning to design the loss function to solve the fuzzy problem of regression-to-the-mean when regressing Heatmap. The second-stage network is used as the generator, and the discriminator is designed to define the loss function to judge the reliability of the generated Heatmap (AU)

Sequence- and Structure-Based Mining of Thermostable D-Allulose 3-Epimerase and Computer-Guided Protein Engineering To Improve Enzyme Activity.

D-Allulose, a functional sweetener, can be synthesized from fructose using D-allulose 3-epimerase (DAEase). Nevertheless, a majority of the reported DAEases have inadequate stability under harsh industrial reaction conditions, which greatly limits their practical applications. In this study, big data mining combined with a computer-guided free energy calculation strategy was employed to discover a novel DAEase with excellent thermostability. Consensus sequence analysis of flexible regions and comparison of binding energies after substrate docking were performed using phylogeny-guided big data analyses. TtDAE from Thermogutta terrifontis was the most thermostable among 358 candidate enzymes, with a half-life of 32 h at 70 °C. Subsequently, structure-guided virtual screening and a customized strategy based on a combinatorial active-site saturation test/iterative saturation mutagenesis were utilized to engineer TtDAE. Finally, the catalytic activity of the M4 variant (P105A/L14C/T63G/I65A) was increased by 5.12-fold. Steered molecular dynamics simulations indicated that M4 had an enlarged substrate-binding pocket, which enhanced the fit between the enzyme and the substrate. The approach presented here, combining DAEases mining with further rational modification, provides guidance for obtaining promising catalysts for industrial-scale production.

Genome Study of α-, ß-, and γ-Carbonic Anhydrases from the Thermophilic Microbiome of Marine Hydrothermal Vent Ecosystems.

Carbonic anhydrases (CAs) are metalloenzymes that can help organisms survive in hydrothermal vents by hydrating carbon dioxide (CO2). In this study, we focus on alpha (α), beta (ß), and gamma (γ) CAs, which are present in the thermophilic microbiome of marine hydrothermal vents. The coding genes of these enzymes can be transferred between hydrothermal-vent organisms via horizontal gene transfer (HGT), which is an important tool in natural biodiversity. We performed big data mining and bioinformatics studies on α-, ß-, and γ-CA coding genes from the thermophilic microbiome of marine hydrothermal vents. The results showed a reasonable association between thermostable α-, ß-, and γ-CAs in the microbial population of the hydrothermal vents. This relationship could be due to HGT. We found evidence of HGT of α- and ß-CAs between Cycloclasticus sp., a symbiont of Bathymodiolus heckerae, and an endosymbiont of Riftia pachyptila via Integrons. Conversely, HGT of ß-CA genes from the endosymbiont Tevnia jerichonana to the endosymbiont Riftia pachyptila was detected. In addition, Hydrogenovibrio crunogenus SP-41 contains a ß-CA gene on genomic islands (GIs). This gene can be transferred by HGT to Hydrogenovibrio sp. MA2-6, a methanotrophic endosymbiont of Bathymodiolus azoricus, and a methanotrophic endosymbiont of Bathymodiolus puteoserpentis. The endosymbiont of R. pachyptila has a γ-CA gene in the genome. If α- and ß-CA coding genes have been derived from other microorganisms, such as endosymbionts of T. jerichonana and Cycloclasticus sp. as the endosymbiont of B. heckerae, through HGT, the theory of the necessity of thermostable CA enzymes for survival in the extreme ecosystem of hydrothermal vents is suggested and helps the conservation of microbiome natural diversity in hydrothermal vents. These harsh ecosystems, with their integral players, such as HGT and endosymbionts, significantly impact the enrichment of life on Earth and the carbon cycle in the ocean.

Methods for Analyzing the Contents of Social Media for Health Care: Scoping Review.

BACKGROUND: Given the rapid development of social media, effective extraction and analysis of the contents of social media for health care have attracted widespread attention from health care providers. As far as we know, most of the reviews focus on the application of social media, and there is a lack of reviews that integrate the methods for analyzing social media information for health care. OBJECTIVE: This scoping review aims to answer the following 4 questions: (1) What types of research have been used to investigate social media for health care, (2) what methods have been used to analyze the existing health information on social media, (3) what indicators should be applied to collect and evaluate the characteristics of methods for analyzing the contents of social media for health care, and (4) what are the current problems and development directions of methods used to analyze the contents of social media for health care? METHODS: A scoping review following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines was conducted. We searched PubMed, the Web of Science, EMBASE, the Cumulative Index to Nursing and Allied Health Literature, and the Cochrane Library for the period from 2010 to May 2023 for primary studies focusing on social media and health care. Two independent reviewers screened eligible studies against inclusion criteria. A narrative synthesis of the included studies was conducted. RESULTS: Of 16,161 identified citations, 134 (0.8%) studies were included in this review. These included 67 (50.0%) qualitative designs, 43 (32.1%) quantitative designs, and 24 (17.9%) mixed methods designs. The applied research methods were classified based on the following aspects: (1) manual analysis methods (content analysis methodology, grounded theory, ethnography, classification analysis, thematic analysis, and scoring tables) and computer-aided analysis methods (latent Dirichlet allocation, support vector machine, probabilistic clustering, image analysis, topic modeling, sentiment analysis, and other natural language processing technologies), (2) categories of research contents, and (3) health care areas (health practice, health services, and health education). CONCLUSIONS: Based on an extensive literature review, we investigated the methods for analyzing the contents of social media for health care to determine the main applications, differences, trends, and existing problems. We also discussed the implications for the future. Traditional content analysis is still the mainstream method for analyzing social media content, and future research may be combined with big data research. With the progress of computers, mobile phones, smartwatches, and other smart devices, social media information sources will become more diversified. Future research can combine new sources, such as pictures, videos, and physiological signals, with online social networking to adapt to the development trend of the internet. More medical information talents need to be trained in the future to better solve the problem of network information analysis. Overall, this scoping review can be useful for a large audience that includes researchers entering the field.

Facilitating COVID recognition from X-rays with computer vision models and transfer learning.

Multimedia data plays an important role in medicine and healthcare since EHR (Electronic Health Records) entail complex images and videos for analyzing patient data. In this article, we hypothesize that transfer learning with computer vision can be adequately harnessed on such data, more specifically chest X-rays, to learn from a few images for assisting accurate, efficient recognition of COVID. While researchers have analyzed medical data (including COVID data) using computer vision models, the main contributions of our study entail the following. Firstly, we conduct transfer learning using a few images from publicly available big data on chest X-rays, suitably adapting computer vision models with data augmentation. Secondly, we aim to find the best fit models to solve this problem, adjusting the number of samples for training and validation to obtain the minimum number of samples with maximum accuracy. Thirdly, our results indicate that combining chest radiography with transfer learning has the potential to improve the accuracy and timeliness of radiological interpretations of COVID in a cost-effective manner. Finally, we outline applications of this work during COVID and its recovery phases with future issues for research and development. This research exemplifies the use of multimedia technology and machine learning in healthcare.

Air travel demand forecasting based on big data: A struggle against public anxiety.

It is of great significance to accurately grasp the demand for air travel to promote the revival of long-distance travel and alleviate public anxiety. The main purpose of this study is to build a high-precision air travel demand forecasting framework by introducing effective Internet data. In the age of big data, passengers before traveling often look for reference groups in search engines and make travel decisions under their informational influence. The big data generated based on these behaviors can reflect the overall passenger psychology and travel demand. Therefore, based on big data mining technology, this study designed a strict dual data preprocessing method and an ensemble forecasting framework, introduced search engine data into the air travel demand forecasting process, and conducted empirical research based on the dataset composed of air travel volume of Shanghai Pudong International Airport. The results show that effective search engine data is helpful to air travel demand forecasting. This research provides a theoretical basis for the application of big data mining technology and data spatial information in air travel demand forecasting and tourism management, and provides a new idea for alleviating public anxiety.

Emotional analysis of evaluation discourse in business English translation based on language big data mining of public health environment.

Purpose: This paper conducts sentiment analysis on the evaluation discourse of business English translation based on language big data mining of public health environment, and aims to find a reasonable algorithm to conduct detailed research on all aspects of sentiment analysis. Methodology: This paper focuses on three areas of sentiment information, extraction, sentiment information retrieval, and sentiment information submission, using scale analysis and feedback analysis, combined with related algorithms of big data mining technology, such as decision trees and clustering algorithms, through the level of emotional words appearing in the corpus, phrase-level, text-level, etc., and combine the text model with the combined reliability to output the evaluation object and evaluation feature separately, and propose an evaluation method to calculate the sensitivity of the evaluation feature, so as to accurately improve the sensitivity of the evaluation feature. It is mainly divided into two categories for data analysis. One is to focus on the public health environment of the characteristics of business English translation itself, and the other is to conduct research on the application of big data mining in the evaluation of translation discourse. Research findings: The research data show that the smallest gap between the sentiment orientation of the discourse evaluation perspective is the output of the language discourse, and the smallest gap in the attributes of the evaluation object is at the phrase level, and the gap value is 3.5; for the evaluation object, the maximum difference is 3.4. Research implications: With the development of science and technology and the economy, the public health environment has become more and more complex, and business English translation has received more and more attention. The sentiment analysis of evaluation discourse in this field is a means of expressing language characteristics. In order to enrich research in this field, the study of this article is necessary. Practical implications: This study has a deeper understanding of the affective analysis of evaluation discourse in public health environment business English translation. The clustering algorithm of big data mining technology applied can provide an important guarantee for the actual conclusion of this research and quantitative analysis of the positive evaluation and criticism of evaluation. To solve the various problems encountered in translation, so as to improve the translator's own translation level, and promote the research of translation methods in Chinese translation.

Spatio-temporal estimation of wind speed and wind power using extreme learning machines: predictions, uncertainty and technical potential.

With wind power providing an increasing amount of electricity worldwide, the quantification of its spatio-temporal variations and the related uncertainty is crucial for energy planners and policy-makers. Here, we propose a methodological framework which (1) uses machine learning to reconstruct a spatio-temporal field of wind speed on a regular grid from spatially irregularly distributed measurements and (2) transforms the wind speed to wind power estimates. Estimates of both model and prediction uncertainties, and of their propagation after transforming wind speed to power, are provided without any assumptions on data distributions. The methodology is applied to study hourly wind power potential on a grid of 250 × 250  m 2 for turbines of 100 m hub height in Switzerland, generating the first dataset of its type for the country. We show that the average annual power generation per turbine is 4.4 GWh. Results suggest that around 12,000 wind turbines could be installed on all 19,617 km 2 of available area in Switzerland resulting in a maximum technical wind potential of 53 TWh. To achieve the Swiss expansion goals of wind power for 2050, around 1000 turbines would be sufficient, corresponding to only 8% of the maximum estimated potential. Supplementary Information: The online version contains supplementary material available at 10.1007/s00477-022-02219-w.

Analysis of the Psychological Barriers to Spoken English From Big Data and Cross-Cultural Perspectives.

College English teaching aims to cultivate students' comprehensive ability to use English. The study of spoken English barriers is a hot topic in this subject area. Based on a survey of non-English primary college students' spoken language impairments, this paper analyzes the research status of spoken language impairments at home and abroad. It relies upon the theoretical basis of Swain's output and Krashen's input hypotheses. With extensive data mining in colleges and universities as the entry point, this paper's content, object, and method are determined by combining qualitative and quantitative research with empirical research. Through the combination of classroom observations, questionnaires, interviews, and other research forms, this paper concludes that the spoken language barriers of non-English primary college students include language and non-language barriers. The influencing factors of the spoken language output barriers include subjective and objective aspects. The questionnaires are analyzed from the three dimensions of the students, schools, and education departments. This paper proposes some ways to overcome the spoken English barriers of non-English college students. It also suggests that non-English college teachers should pay more attention to the cultural transmission of English-speaking countries in English classes, cultivate students' cross-cultural awareness, and enhance students' enthusiasm in English learning. These actions are more conducive to overcoming the psychological barriers in spoken English output.

Integration of Transcriptomics Data and Metabolomic Data Using Biomedical Literature Mining and Pathway Analysis.

Recent progress in omics technologies such as transcriptomics and metabolomics offers an unprecedented opportunity to understand the disease mechanisms and determines the associated biomedical entities using biomedical literature mining. Tremendous data available in the biomedical literature helps in addressing complex biomedical problems. Advancements in genomics and transcriptomics helps in decoding the genetic information obtained from various high throughput techniques for its use in personalized medicine and therapeutics. Integration of data from biomedical literature and data from large-scale genomic studies aids in the determination of the etiology of a disease and drug targets. This chapter addresses the perspectives of transcriptomics and metabolomics in biomedical literature mining and gives an overview of state-of-the-art techniques in this field.

Establishment of Reference Interval and Aging Model of Homocysteine Using Real-World Data.

Objective: The level of Homocysteine (Hcy) in males is generally higher than that of females, but the same reference interval (RI) is often used in clinical practice. This study aims to establish a sex-specific RI of Hcy using five data mining algorithms and compare these results. Furthermore, age-related continuous RI was established in order to show the relationship between Hcy concentration distribution and age. Methods: A total of 20,801 individuals were included in the study and Tukey method was used to identify outliers in subgroups by sex and age. Multiple linear regression and standard deviation ratio (SDR) was used to determine whether the RI for Hcy needs to be divided by sex and age. Five algorithms including Hoffmann, Bhattacharya, expectation maximization (EM), kosmic and refineR were utilized to establish the RI of Hcy. Generalized Additive Models for Location Scale and Shape (GAMLSS) algorithm was used to determine the aging model of Hcy and calculate the age-related continuous RI. Results: RI of Hcy needed to be partitioned by sex (SDR = 0.735 > 0.375). RIs established by Hoffmann, Bhattacharya, EM (for females) and kosmic are all within the 95% CI of reference limits established by refine R. The Sex-specific aging model of Hcy showed that the upper limits of the RI of Hcy declined with age beginning at age of 18 and began to rise approximately after age of 40 for females and increased with age for males. Conclusion: The RI of Hcy needs to be partitioned by sex. The RIs established by the five data mining algorithms showed good consistency. The dynamic sex and age-specific model of Hcy showed the pattern of Hcy concentration with age and provide more personalized tools for clinical decisions.

A Web Application for Interactive Visualization of European Basketball Data.

The statistical analysis of basketball games is a fast-growing field. Certainly, basketball data are scientifically relevant because an appropriate analysis provides a great deal of information about the performance of both players and teams. The number of games played each season generates a large amount of data worth analyzing. Basketball analytics is well established in U.S. leagues. In Europe, however, it has not been duly developed. This study focuses on the top three European team competitions: the EuroLeague, the EuroCup, and the Spanish ACB (Association of Basketball Clubs, acronym in Spanish) league. Their official websites provide access to game data for anyone who is interested, but they are only represented in a static tabular form. As a consequence, it is difficult to gain any valuable insights from them. This article presents a highly useful interactive tool, created with the free statistical software R, which makes it possible to visualize and explore basketball data from a large number of seasons. We will demonstrate its core functionality. An accompanying R package is presented in the Supplementary Data.

Prevention and Control of Pathogens Based on Big-Data Mining and Visualization Analysis.

Morbidity and mortality caused by infectious diseases rank first among all human illnesses. Many pathogenic mechanisms remain unclear, while misuse of antibiotics has led to the emergence of drug-resistant strains. Infectious diseases spread rapidly and pathogens mutate quickly, posing new threats to human health. However, with the increasing use of high-throughput screening of pathogen genomes, research based on big data mining and visualization analysis has gradually become a hot topic for studies of infectious disease prevention and control. In this paper, the framework was performed on four infectious pathogens (Fusobacterium, Streptococcus, Neisseria, and Streptococcus salivarius) through five functions: 1) genome annotation, 2) phylogeny analysis based on core genome, 3) analysis of structure differences between genomes, 4) prediction of virulence genes/factors with their pathogenic mechanisms, and 5) prediction of resistance genes/factors with their signaling pathways. The experiments were carried out from three angles: phylogeny (macro perspective), structure differences of genomes (micro perspective), and virulence and drug-resistance characteristics (prediction perspective). Therefore, the framework can not only provide evidence to support the rapid identification of new or unknown pathogens and thus plays a role in the prevention and control of infectious diseases, but also help to recommend the most appropriate strains for clinical and scientific research. This paper presented a new genome information visualization analysis process framework based on big data mining technology with the accommodation of the depth and breadth of pathogens in molecular level research.

Ship Spatiotemporal Key Feature Point Online Extraction Based on AIS Multi-Sensor Data Using an Improved Sliding Window Algorithm.

Large volumes of automatic identification system (AIS) data provide new ideas and methods for ship data mining and navigation behavior pattern analysis. However, large volumes of big data have low unit values, resulting in the need for large-scale computing, storage, and display. Learning efficiency is low and learning direction is blind and untargeted. Therefore, key feature point (KFP) extraction from the ship trajectory plays an important role in fields such as ship navigation behavior analysis and big data mining. In this paper, we propose a ship spatiotemporal KFP online extraction algorithm that is applied to AIS trajectory data. The sliding window algorithm is modified for application to ship navigation angle deviation, position deviation, and the spatiotemporal characteristics of AIS data. Next, in order to facilitate the subsequent use of the algorithm, a recommended threshold range for the corresponding two parameters is discussed. Finally, the performance of the proposed method is compared with that of the Douglas-Peucker (DP) algorithm to assess its feature extraction accuracy and operational efficiency. The results show that the proposed improved sliding window algorithm can be applied to rapidly and easily extract the KFPs from AIS trajectory data. This ability provides significant benefits for ship traffic flow and navigational behavior learning.

Improving the Accuracy of Feature Selection in Big Data Mining Using Accelerated Flower Pollination (AFP) Algorithm.

In recent times, the main problem associated with big data analytics is its high dimensional data over the search space. Such data gathers continuously in search space making traditional algorithms infeasible for data mining in real time environment. Hence, feature selection is an important method to lighten the load during processing while inducing a model for mining. However, mining over such high dimensional data leads to formulation of optimal feature subset, which grows exponentially and leads to intractable computational demand. In this paper, a novel lightweight mechanism is used as a feature selection method, which solves the after effects arising with optimal feature selection. The feature selection in big data mining is done using accelerated flower pollination (AFP) algorithm. This method improves the accuracy of feature selection with reduced processing time. The proposed method is tested under larger set of data with high dimensionality to test the performance of proposed method.

Big-Data-Mining-Based Improved K-Means Algorithm for Energy Use Analysis of Coal-Fired Power Plant Units: A Case Study.

The energy use analysis of coal-fired power plant units is of significance for energy conservation and consumption reduction. One of the most serious problems attributed to Chinese coal-fired power plants is coal waste. Several units in one plant may experience a practical rated output situation at the same time, which may increase the coal consumption of the power plant. Here, we propose a new hybrid methodology for plant-level load optimization to minimize coal consumption for coal-fired power plants. The proposed methodology includes two parts. One part determines the reference value of the controllable operating parameters of net coal consumption under typical load conditions, based on an improved K-means algorithm and the Hadoop platform. The other part utilizes a support vector machine to determine the sensitivity coefficients of various operating parameters for the net coal consumption under different load conditions. Additionally, the fuzzy rough set attribute reduction method was employed to obtain the minimalist properties reduction method parameters to reduce the complexity of the dataset. This work is based on continuously-measured information system data from a 600 MW coal-fired power plant in China. The results show that the proposed strategy achieves high energy conservation performance. Taking the 600 MW load optimization value as an example, the optimized power supply coal consumption is 307.95 g/(kW·h) compared to the actual operating value of 313.45 g/(kW·h). It is important for coal-fired power plants to reduce their coal consumption.

Sparse generalized linear model with L0 approximation for feature selection and prediction with big omics data.

BACKGROUND: Feature selection and prediction are the most important tasks for big data mining. The common strategies for feature selection in big data mining are L1, SCAD and MC+. However, none of the existing algorithms optimizes L0, which penalizes the number of nonzero features directly. RESULTS: In this paper, we develop a novel sparse generalized linear model (GLM) with L0 approximation for feature selection and prediction with big omics data. The proposed approach approximate the L0 optimization directly. Even though the original L0 problem is non-convex, the problem is approximated by sequential convex optimizations with the proposed algorithm. The proposed method is easy to implement with only several lines of code. Novel adaptive ridge algorithms (L0ADRIDGE) for L0 penalized GLM with ultra high dimensional big data are developed. The proposed approach outperforms the other cutting edge regularization methods including SCAD and MC+ in simulations. When it is applied to integrated analysis of mRNA, microRNA, and methylation data from TCGA ovarian cancer, multilevel gene signatures associated with suboptimal debulking are identified simultaneously. The biological significance and potential clinical importance of those genes are further explored. CONCLUSIONS: The developed Software L0ADRIDGE in MATLAB is available at https://github.com/liuzqx/L0adridge.