Dimitrios I. Bourdas, Panteleimon Bakirtzoglou, Antonios K. Travlos, Vasileios Andrianopoulos, E. Zacharakis
This dataset aimed to explore associations between pre-SARS-CoV-2 infection exercise and sports-related physical activity (PA) levels and disease severity, along with treatments administered following the most recent SARS-CoV-2 infection. A comprehensive analysis investigated the relationships between PA categories (“Inactive”, “Low PA”, “Moderate PA”, “High PA”), disease severity (“Sporadic”, “Episodic”, “Recurrent”, “Frequent”, “Persistent”), and treatments post-SARS-CoV-2 infection (“No treatment”, “Home remedies”, “Prescribed medication”, “Hospital admission”, “Intensive care unit admission”) within a sample population (n = 5829) from the Hellenic territory. Utilizing the Active-Q questionnaire, data were collected from February to March 2023, capturing PA habits, participant characteristics, medical history, vaccination status, and illness experiences. Findings revealed an independent relationship between preinfection PA levels and disease severity (χ2 = 9.097, df = 12, p = 0.695). Additionally, a statistical dependency emerged between PA levels and illness treatment categories (χ2 = 39.362, df = 12, p < 0.001), particularly linking inactive PA with home remedies treatment. These results highlight the potential influence of preinfection PA on disease severity and treatment choices following SARS-CoV-2 infection. The dataset offers valuable insights into the interplay between PA, disease outcomes, and treatment decisions, aiding future research in shaping targeted interventions and public health strategies related to COVID-19 management.
{"title":"Comprehensive Dataset on Pre-SARS-CoV-2 Infection Sports-Related Physical Activity Levels, Disease Severity, and Treatment Outcomes: Insights and Implications for COVID-19 Management","authors":"Dimitrios I. Bourdas, Panteleimon Bakirtzoglou, Antonios K. Travlos, Vasileios Andrianopoulos, E. Zacharakis","doi":"10.3390/data9020023","DOIUrl":"https://doi.org/10.3390/data9020023","url":null,"abstract":"This dataset aimed to explore associations between pre-SARS-CoV-2 infection exercise and sports-related physical activity (PA) levels and disease severity, along with treatments administered following the most recent SARS-CoV-2 infection. A comprehensive analysis investigated the relationships between PA categories (“Inactive”, “Low PA”, “Moderate PA”, “High PA”), disease severity (“Sporadic”, “Episodic”, “Recurrent”, “Frequent”, “Persistent”), and treatments post-SARS-CoV-2 infection (“No treatment”, “Home remedies”, “Prescribed medication”, “Hospital admission”, “Intensive care unit admission”) within a sample population (n = 5829) from the Hellenic territory. Utilizing the Active-Q questionnaire, data were collected from February to March 2023, capturing PA habits, participant characteristics, medical history, vaccination status, and illness experiences. Findings revealed an independent relationship between preinfection PA levels and disease severity (χ2 = 9.097, df = 12, p = 0.695). Additionally, a statistical dependency emerged between PA levels and illness treatment categories (χ2 = 39.362, df = 12, p < 0.001), particularly linking inactive PA with home remedies treatment. These results highlight the potential influence of preinfection PA on disease severity and treatment choices following SARS-CoV-2 infection. The dataset offers valuable insights into the interplay between PA, disease outcomes, and treatment decisions, aiding future research in shaping targeted interventions and public health strategies related to COVID-19 management.","PeriodicalId":502371,"journal":{"name":"Data","volume":"27 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139595793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The infections caused by various bacterial pathogens both in clinical and community settings represent a significant threat to public healthcare worldwide. The growing resistance to antimicrobial drugs acquired by bacterial species causing healthcare-associated infections has already become a life-threatening danger noticed by the World Health Organization. Several groups or lineages of bacterial isolates, usually called ‘the clones of high risk’, often drive the spread of resistance within particular species. Thus, it is vitally important to reveal and track the spread of such clones and the mechanisms by which they acquire antibiotic resistance and enhance their survival skills. Currently, the analysis of whole-genome sequences for bacterial isolates of interest is increasingly used for these purposes, including epidemiological surveillance and the development of spread prevention measures. However, the availability and uniformity of the data derived from genomic sequences often represent a bottleneck for such investigations. With this dataset, we present the results of a genomic epidemiology analysis of 17,546 genomes of a dangerous bacterial pathogen, Acinetobacter baumannii. Important typing information, including multilocus sequence typing (MLST)-based sequence types (STs), intrinsic blaOXA-51-like gene variants, capsular (KL) and oligosaccharide (OCL) types, CRISPR-Cas systems, and cgMLST profiles are presented, as well as the assignment of particular isolates to nine known international clones of high risk. The presence of antimicrobial resistance genes within the genomes is also reported. These data will be useful for researchers in the field of A. baumannii genomic epidemiology, resistance analysis, and prevention measure development.
{"title":"Genomic Epidemiology Dataset for the Important Nosocomial Pathogenic Bacterium Acinetobacter baumannii","authors":"A. Shelenkov, Yu. D. Mikhaylova, Vasiliy Akimkin","doi":"10.3390/data9020022","DOIUrl":"https://doi.org/10.3390/data9020022","url":null,"abstract":"The infections caused by various bacterial pathogens both in clinical and community settings represent a significant threat to public healthcare worldwide. The growing resistance to antimicrobial drugs acquired by bacterial species causing healthcare-associated infections has already become a life-threatening danger noticed by the World Health Organization. Several groups or lineages of bacterial isolates, usually called ‘the clones of high risk’, often drive the spread of resistance within particular species. Thus, it is vitally important to reveal and track the spread of such clones and the mechanisms by which they acquire antibiotic resistance and enhance their survival skills. Currently, the analysis of whole-genome sequences for bacterial isolates of interest is increasingly used for these purposes, including epidemiological surveillance and the development of spread prevention measures. However, the availability and uniformity of the data derived from genomic sequences often represent a bottleneck for such investigations. With this dataset, we present the results of a genomic epidemiology analysis of 17,546 genomes of a dangerous bacterial pathogen, Acinetobacter baumannii. Important typing information, including multilocus sequence typing (MLST)-based sequence types (STs), intrinsic blaOXA-51-like gene variants, capsular (KL) and oligosaccharide (OCL) types, CRISPR-Cas systems, and cgMLST profiles are presented, as well as the assignment of particular isolates to nine known international clones of high risk. The presence of antimicrobial resistance genes within the genomes is also reported. These data will be useful for researchers in the field of A. baumannii genomic epidemiology, resistance analysis, and prevention measure development.","PeriodicalId":502371,"journal":{"name":"Data","volume":"27 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139595771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Shaikh, Douglas Chai, Syed Mohammed Shamsul Islam, Naveed Akhtar
Audio-image representations for a multimodal human action (MHAiR) dataset contains six different image representations of the audio signals that capture the temporal dynamics of the actions in a very compact and informative way. The dataset was extracted from the audio recordings which were captured from an existing video dataset, i.e., UCF101. Each data sample captured a duration of approximately 10 s long, and the overall dataset was split into 4893 training samples and 1944 testing samples. The resulting feature sequences were then converted into images, which can be used for human action recognition and other related tasks. These images can be used as a benchmark dataset for evaluating the performance of machine learning models for human action recognition and related tasks. These audio-image representations could be suitable for a wide range of applications, such as surveillance, healthcare monitoring, and robotics. The dataset can also be used for transfer learning, where pre-trained models can be fine-tuned on a specific task using specific audio images. Thus, this dataset can facilitate the development of new techniques and approaches for improving the accuracy of human action-related tasks and also serve as a standard benchmark for testing the performance of different machine learning models and algorithms.
{"title":"MHAiR: A Dataset of Audio-Image Representations for Multimodal Human Actions","authors":"M. Shaikh, Douglas Chai, Syed Mohammed Shamsul Islam, Naveed Akhtar","doi":"10.3390/data9020021","DOIUrl":"https://doi.org/10.3390/data9020021","url":null,"abstract":"Audio-image representations for a multimodal human action (MHAiR) dataset contains six different image representations of the audio signals that capture the temporal dynamics of the actions in a very compact and informative way. The dataset was extracted from the audio recordings which were captured from an existing video dataset, i.e., UCF101. Each data sample captured a duration of approximately 10 s long, and the overall dataset was split into 4893 training samples and 1944 testing samples. The resulting feature sequences were then converted into images, which can be used for human action recognition and other related tasks. These images can be used as a benchmark dataset for evaluating the performance of machine learning models for human action recognition and related tasks. These audio-image representations could be suitable for a wide range of applications, such as surveillance, healthcare monitoring, and robotics. The dataset can also be used for transfer learning, where pre-trained models can be fine-tuned on a specific task using specific audio images. Thus, this dataset can facilitate the development of new techniques and approaches for improving the accuracy of human action-related tasks and also serve as a standard benchmark for testing the performance of different machine learning models and algorithms.","PeriodicalId":502371,"journal":{"name":"Data","volume":"17 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139597532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Feature selection is a significant issue in the machine learning process. Most datasets include features that are not needed for the problem being studied. These irrelevant features reduce both the efficiency and accuracy of the algorithm. It is possible to think about feature selection as an optimization problem. Swarm intelligence algorithms are promising techniques for solving this problem. This research paper presents a hybrid approach for tackling the problem of feature selection. A filter method (chi-square) and two wrapper swarm intelligence algorithms (grey wolf optimization (GWO) and particle swarm optimization (PSO)) are used in two different techniques to improve feature selection accuracy and system execution time. The performance of the two phases of the proposed approach is assessed using two distinct datasets. The results show that PSOGWO yields a maximum accuracy boost of 95.3%, while chi2-PSOGWO yields a maximum accuracy improvement of 95.961% for feature selection. The experimental results show that the proposed approach performs better than the compared approaches.
{"title":"An Optimized Hybrid Approach for Feature Selection Based on Chi-Square and Particle Swarm Optimization Algorithms","authors":"A. Abdo, Rasha Mostafa, Laila Abdelhamid","doi":"10.3390/data9020020","DOIUrl":"https://doi.org/10.3390/data9020020","url":null,"abstract":"Feature selection is a significant issue in the machine learning process. Most datasets include features that are not needed for the problem being studied. These irrelevant features reduce both the efficiency and accuracy of the algorithm. It is possible to think about feature selection as an optimization problem. Swarm intelligence algorithms are promising techniques for solving this problem. This research paper presents a hybrid approach for tackling the problem of feature selection. A filter method (chi-square) and two wrapper swarm intelligence algorithms (grey wolf optimization (GWO) and particle swarm optimization (PSO)) are used in two different techniques to improve feature selection accuracy and system execution time. The performance of the two phases of the proposed approach is assessed using two distinct datasets. The results show that PSOGWO yields a maximum accuracy boost of 95.3%, while chi2-PSOGWO yields a maximum accuracy improvement of 95.961% for feature selection. The experimental results show that the proposed approach performs better than the compared approaches.","PeriodicalId":502371,"journal":{"name":"Data","volume":"43 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139598152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
O. Kulaeva, E. Zorin, A. Sulima, G. Akhtemova, Vladimir A Zhukov
Legume plants enter a symbiosis with soil nitrogen-fixing bacteria (rhizobia), thereby gaining access to assimilable atmospheric nitrogen. Since this symbiosis is important for agriculture, biofertilizers with effective strains of rhizobia are created for crop legumes to increase their yield and minimize the amounts of mineral fertilizers required. In this work, we sequenced and characterized the genome of Rhizobium ruizarguesonis bv. viciae strain RCAM1022, a component of the ‘Rhizotorfin’ biofertilizer produced in Russia and used for pea (Pisum sativum L.).
{"title":"Draft Genome Sequence of the Commercial Strain Rhizobium ruizarguesonis bv. viciae RCAM1022","authors":"O. Kulaeva, E. Zorin, A. Sulima, G. Akhtemova, Vladimir A Zhukov","doi":"10.3390/data9020019","DOIUrl":"https://doi.org/10.3390/data9020019","url":null,"abstract":"Legume plants enter a symbiosis with soil nitrogen-fixing bacteria (rhizobia), thereby gaining access to assimilable atmospheric nitrogen. Since this symbiosis is important for agriculture, biofertilizers with effective strains of rhizobia are created for crop legumes to increase their yield and minimize the amounts of mineral fertilizers required. In this work, we sequenced and characterized the genome of Rhizobium ruizarguesonis bv. viciae strain RCAM1022, a component of the ‘Rhizotorfin’ biofertilizer produced in Russia and used for pea (Pisum sativum L.).","PeriodicalId":502371,"journal":{"name":"Data","volume":"62 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139604455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Appeals to governments for implementing basic income are contemporary. The theoretical backgrounds of the basic income notion only prescribe transferring equal amounts to individuals irrespective of their specific attributes. However, the most recent basic income initiatives all around the world are attached to certain rules with regard to the attributes of the households. This approach is facing significant challenges to appropriately recognize vulnerable groups. A possible alternative for setting rules with regard to the welfare attributes of the households is to employ artificial intelligence algorithms that can process unprecedented amounts of data. Can integrating machine learning change the future of basic income by predicting households vulnerable to future poverty? In this paper, we utilize multidimensional and longitudinal welfare data comprising one and a half million individuals’ data and a Bayesian beliefs network approach to examine the feasibility of predicting households’ vulnerability to future poverty based on the existing households’ welfare attributes.
{"title":"Can Data and Machine Learning Change the Future of Basic Income Models? A Bayesian Belief Networks Approach","authors":"Hamed Khalili","doi":"10.3390/data9020018","DOIUrl":"https://doi.org/10.3390/data9020018","url":null,"abstract":"Appeals to governments for implementing basic income are contemporary. The theoretical backgrounds of the basic income notion only prescribe transferring equal amounts to individuals irrespective of their specific attributes. However, the most recent basic income initiatives all around the world are attached to certain rules with regard to the attributes of the households. This approach is facing significant challenges to appropriately recognize vulnerable groups. A possible alternative for setting rules with regard to the welfare attributes of the households is to employ artificial intelligence algorithms that can process unprecedented amounts of data. Can integrating machine learning change the future of basic income by predicting households vulnerable to future poverty? In this paper, we utilize multidimensional and longitudinal welfare data comprising one and a half million individuals’ data and a Bayesian beliefs network approach to examine the feasibility of predicting households’ vulnerability to future poverty based on the existing households’ welfare attributes.","PeriodicalId":502371,"journal":{"name":"Data","volume":"52 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139603600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Elliott State Research Forest comprises 33,700 ha of temperate, Douglas-fir rainforest along North America’s Pacific Coast (Oregon, United States). In 2015, naturally regenerated stands at least 92 years old covered 49% of the research area and sawtimber plantations younger than 68 years another 50%. During the winter of 2015–2016, a forest wide inventory sampled both naturally regenerated and plantation stands, recording 97,424 trees on 17,866 plots in 738 stands. The resulting dataset is atypical for the area as plot locations were not restricted to upland, commercially harvestable timber. Multiage stands and riparian areas were therefore documented along with plantations 2–61 years old and trees retained through clearcut harvests. This dataset constitutes the only open access, stand-based forest inventory currently available for a large area within the Oregon Coast Range. The dataset enables development of suites of models as well as many comparisons across stand ages and types, both at stand level and at the level of individual trees.
{"title":"Elliott State Research Forest Timber Cruise, Oregon, 2015–2016","authors":"Todd West, Bogdan M. Strimbu","doi":"10.3390/data9010016","DOIUrl":"https://doi.org/10.3390/data9010016","url":null,"abstract":"The Elliott State Research Forest comprises 33,700 ha of temperate, Douglas-fir rainforest along North America’s Pacific Coast (Oregon, United States). In 2015, naturally regenerated stands at least 92 years old covered 49% of the research area and sawtimber plantations younger than 68 years another 50%. During the winter of 2015–2016, a forest wide inventory sampled both naturally regenerated and plantation stands, recording 97,424 trees on 17,866 plots in 738 stands. The resulting dataset is atypical for the area as plot locations were not restricted to upland, commercially harvestable timber. Multiage stands and riparian areas were therefore documented along with plantations 2–61 years old and trees retained through clearcut harvests. This dataset constitutes the only open access, stand-based forest inventory currently available for a large area within the Oregon Coast Range. The dataset enables development of suites of models as well as many comparisons across stand ages and types, both at stand level and at the level of individual trees.","PeriodicalId":502371,"journal":{"name":"Data","volume":"119 40","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139615177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine learning (ML) methods are commonly applied in the fields of extraterrestrial physics, space science, and plasma physics. In a prior publication, an ML classification technique, the Random Forest (RF) algorithm, was utilized to automatically identify and categorize erroneous signals, including instrument errors, noisy signals, outlier data points, and the impact of solar flares (SFs) on the ionosphere. This data communication includes the pre-processed dataset used in the aforementioned research, along with a workflow that utilizes the PyCaret library and a post-processing workflow. The code and data serve educational purposes in the interdisciplinary field of ML and ionospheric physics science, as well as being useful to other researchers for diverse objectives.
机器学习（ML）方法通常应用于地外物理学、空间科学和等离子物理学领域。在之前发表的一篇文章中，使用了一种 ML 分类技术，即随机森林（RF）算法，来自动识别和分类错误信号，包括仪器误差、噪声信号、离群数据点以及太阳耀斑（SF）对电离层的影响。此次数据交流包括上述研究中使用的预处理数据集，以及利用 PyCaret 库的工作流程和后处理工作流程。这些代码和数据可用于 ML 和电离层物理科学跨学科领域的教育目的，也可用于其他研究人员的不同目标。
{"title":"Machine Learning Classification Workflow and Datasets for Ionospheric VLF Data Exclusion","authors":"Filip Arnaut, A. Kolarski, V. Srećković","doi":"10.3390/data9010017","DOIUrl":"https://doi.org/10.3390/data9010017","url":null,"abstract":"Machine learning (ML) methods are commonly applied in the fields of extraterrestrial physics, space science, and plasma physics. In a prior publication, an ML classification technique, the Random Forest (RF) algorithm, was utilized to automatically identify and categorize erroneous signals, including instrument errors, noisy signals, outlier data points, and the impact of solar flares (SFs) on the ionosphere. This data communication includes the pre-processed dataset used in the aforementioned research, along with a workflow that utilizes the PyCaret library and a post-processing workflow. The code and data serve educational purposes in the interdisciplinary field of ML and ionospheric physics science, as well as being useful to other researchers for diverse objectives.","PeriodicalId":502371,"journal":{"name":"Data","volume":"105 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139614503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Malsagova, A. Kopylov, V. Pustovoyt, E. I. Balakin, Ksenia A. Yurku, A. Stepanov, L. Kulikova, V. Rudnev, A. Kaysheva
High exercise loading causes intricate and ambiguous proteomic and metabolic changes. This study aims to describe the dataset on protein and metabolite contents in plasma samples collected from highly trained athletes across different sports disciplines. The proteomic and metabolomic analyses of the plasma samples of highly trained athletes engaged in sports disciplines of different intensities were carried out using HPLC-MS/MS. The results are reported as two datasets (proteomic data in a derived mgf-file and metabolomic data in processed format), each containing the findings obtained by analyzing 93 mass spectra. Variations in the protein and metabolite contents of the biological samples are observed, depending on the intensity of training load for different sports disciplines. Mass spectrometric proteomic and metabolomic studies can be used for classifying different athlete phenotypes according to the intensity of sports discipline and for the assessment of the efficiency of the recovery period.
{"title":"Proteomic and Metabolomic Analyses of the Blood Samples of Highly Trained Athletes","authors":"K. Malsagova, A. Kopylov, V. Pustovoyt, E. I. Balakin, Ksenia A. Yurku, A. Stepanov, L. Kulikova, V. Rudnev, A. Kaysheva","doi":"10.3390/data9010015","DOIUrl":"https://doi.org/10.3390/data9010015","url":null,"abstract":"High exercise loading causes intricate and ambiguous proteomic and metabolic changes. This study aims to describe the dataset on protein and metabolite contents in plasma samples collected from highly trained athletes across different sports disciplines. The proteomic and metabolomic analyses of the plasma samples of highly trained athletes engaged in sports disciplines of different intensities were carried out using HPLC-MS/MS. The results are reported as two datasets (proteomic data in a derived mgf-file and metabolomic data in processed format), each containing the findings obtained by analyzing 93 mass spectra. Variations in the protein and metabolite contents of the biological samples are observed, depending on the intensity of training load for different sports disciplines. Mass spectrometric proteomic and metabolomic studies can be used for classifying different athlete phenotypes according to the intensity of sports discipline and for the assessment of the efficiency of the recovery period.","PeriodicalId":502371,"journal":{"name":"Data","volume":" 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139620005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the era of data-driven technologies, the need for diverse and high-quality datasets for training and testing machine learning models has become increasingly critical. In this article, we present a versatile methodology, the Generic Methodology for Constructing Synthetic Data Generation (GeMSyD), which addresses the challenge of synthetic data creation in the context of smart devices. GeMSyD provides a framework that enables the generation of synthetic datasets, aligning them closely with real-world data. To demonstrate the utility of GeMSyD, we instantiate the methodology by constructing a synthetic data generation framework tailored to the domain of event-based data modeling, specifically focusing on user interactions with smart devices. Our framework leverages GeMSyD to create synthetic datasets that faithfully emulate the dynamics of human–device interactions, including the temporal dependencies. Furthermore, we showcase how the synthetic data generated using our framework can serve as a valuable resource for machine learning practitioners. By employing these synthetic datasets, we perform a series of experiments to evaluate the performance of a neural-network-based prediction model in the domain of smart device interaction. Our results underscore the potential of synthetic data in facilitating model development and benchmarking.
{"title":"GeMSyD: Generic Framework for Synthetic Data Generation","authors":"Ramona Tolas, Raluca Portase, R. Potolea","doi":"10.3390/data9010014","DOIUrl":"https://doi.org/10.3390/data9010014","url":null,"abstract":"In the era of data-driven technologies, the need for diverse and high-quality datasets for training and testing machine learning models has become increasingly critical. In this article, we present a versatile methodology, the Generic Methodology for Constructing Synthetic Data Generation (GeMSyD), which addresses the challenge of synthetic data creation in the context of smart devices. GeMSyD provides a framework that enables the generation of synthetic datasets, aligning them closely with real-world data. To demonstrate the utility of GeMSyD, we instantiate the methodology by constructing a synthetic data generation framework tailored to the domain of event-based data modeling, specifically focusing on user interactions with smart devices. Our framework leverages GeMSyD to create synthetic datasets that faithfully emulate the dynamics of human–device interactions, including the temporal dependencies. Furthermore, we showcase how the synthetic data generated using our framework can serve as a valuable resource for machine learning practitioners. By employing these synthetic datasets, we perform a series of experiments to evaluate the performance of a neural-network-based prediction model in the domain of smart device interaction. Our results underscore the potential of synthetic data in facilitating model development and benchmarking.","PeriodicalId":502371,"journal":{"name":"Data","volume":" 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139626711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：