Description Of Dataset Research Articles

The Office of Water Prediction's Analysis of Record for Calibration, version 1.1: Dataset description and precipitation evaluation

AbstractHydrologic models operated by the National Weather Service call for an accurate, consistent, high‐resolution, multi‐decade, continental‐scale record of hydrometeorological fields to serve as forcing data for model calibration. To serve this purpose, the Analysis of Record for Calibration was developed, and version 1.1 of the dataset is described in this study. Geospatial and scientific requirements, methods used in dataset generation, and input data sources are described. Given the prominent role of precipitation in model calibration, accurate and consistent precipitation is a particularly high priority for the analysis. To evaluate the analysis from this perspective, its daily precipitation is compared with surface observing stations over 43 years. The analysis exhibits low bias compared with other similar products. It also displays nonstationary bias behavior after 2015 due to the lack of a climatological constraint, as well as frequent occurrences of heavy‐to‐extreme precipitation that are often difficult to verify. These findings should be taken into account when the product is used for model calibration.

General Intelligent Dataset Description Method and Application

With the development of the Internet, the growth rate of big data has exceeded the ability of human beings to obtain information from data. In the near future, faced with the sea of data, seemingly logically correct algorithms may come to the opposite conclusion, which will be a “data disaster” era. Therefore, letting data “speak” and enable data intelligence is an important problem that must be solved in the field of big data research. In this paper, we propose a “data intelligence” framework based on Brooks’s Subsumption Architecture for robotics. In this framework, we define a new dataset description method and try to encapsulate the dataset described by this method into a software container. Then, we set up the corresponding operations on the dataset container. Finally, we identify an interaction model for a “dataset agent” based on academic work on agents in the field of artificial intelligence. And we designed and implemented some functions of an intelligent document manager, which proves that our design ideas and methods are feasible.

Application of data fusion for automated detection of children with developmental and mental disorders: A systematic review of the last decade

Mental health is a basic need for a sustainable and developing society. The prevalence and financial burden of mental illness have increased globally, and especially in response to community and worldwide pandemic events. Children suffering from such mental disorders find it difficult to cope with educational, occupational, personal, and societal developments, and treatments are not accessible to all. Advancements in technology have resulted in much research examining the use of artificial intelligence to detect or identify characteristics of mental illness. Therefore, this paper presents a systematic review of nine developmental and mental disorders (Autism spectrum disorder, Attention deficit hyperactivity disorder, Schizophrenia, Anxiety, Depression, Dyslexia, Post-traumatic stress disorder, Tourette syndrome, and Obsessive–compulsive disorder) prominent in children and adolescents. Our paper focuses on the automated detection of these developmental and mental disorders using physiological signals. This paper also presents a detailed discussion on signal analysis, feature engineering, and decision-making with their advantages, future directions and challenges on the papers published on mental disorders of children. We have presented the details of the dataset description, validation techniques, features extracted and decision-making models. The challenges and future directions present open research questions on signal or availability, uncertainty, explainability, and hardware implementation resources for signal analysis and machine or deep learning models. Finally, the main findings of this study are presented in the conclusion section.

Identifying and sharing per-and polyfluoroalkyl substances hot-spot areas and exposures in drinking water

Exposure to per- and polyfluoroalkyl substances (PFAS) in drinking water is widely recognized as a public health concern. Decision-makers who are responsible for managing PFAS drinking water risks lack the tools to acquire the information they need. In response to this need, we provide a detailed description of a Kentucky dataset that allows decision-makers to visualize potential hot-spot areas and evaluate drinking water systems that may be susceptible to PFAS contamination. The dataset includes information extracted from publicly available sources to create five different maps in ArcGIS Online and highlights potential sources of PFAS contamination in the environment in relation to drinking water systems. As datasets of PFAS drinking water sampling continue to grow as part of evolving regulatory requirements, we used this Kentucky dataset as an example to promote the reuse of this dataset and others like it. We incorporated the FAIR (Findable, Accessible, Interoperable, and Reusable) principles by creating a Figshare item that includes all data and associated metadata with these five ArcGIS maps.

Differentially Private Recurrent Variational Autoencoder For Text Privacy Preservation

Deep learning techniques have been widely used in natural language processing (NLP) tasks and have made remarkable progress. However, training the deep learning model relies on a large amount of data which may involve sensitive information like electronic medical records. The attacker can infer sensitive information from the model, which leads to privacy leakage. To solve this problem, we propose a Differentially Private Recurrent Variational AutoEncoder (DP-RVAE) that can generate simulated data in place of the sensitive dataset to preserve privacy. To generate high utility synthetic text, a part of sensitive text data is employed as the conditional input of the model and uses a dropout and noise perturbing mechanism to preserve differential privacy. In addition, we expand the proposed DP-RVAE to a federated learning setting and design a novel training paradigm for NLP tasks. Specifically, DP-RVAE is deployed to the client-side to train and generate personalized text. These DP-RVAE models would be aggregated and updated through the Federated Optimisation (FedOPT) algorithm so that personal information can be well preserved. We evaluate our proposed DP-RVAE through a text classification task on the Tweets depression sentiment and IMDB reviews datasets. Our DP-RVAE achieves a higher average test accuracy by 5.90% and 3.94% compared to the typical centralized training and federated learning approach, respectively. We also perform the keywords inference attack experiment on the medical description dataset collected from the real world. Compared to the typical differentially private preserving approach, the DP-RVAE decreases by 15.2% in average attack accuracy. The experimental results demonstrate that DP-RVAE can be applied to the NLP models to leverage accuracy while preserving sensitive privacy.

A Dataset of Scalp EEG Recordings of Alzheimer’s Disease, Frontotemporal Dementia and Healthy Subjects from Routine EEG

Recently, there has been a growing research interest in utilizing the electroencephalogram (EEG) as a non-invasive diagnostic tool for neurodegenerative diseases. This article provides a detailed description of a resting-state EEG dataset of individuals with Alzheimer’s disease and frontotemporal dementia, and healthy controls. The dataset was collected using a clinical EEG system with 19 scalp electrodes while participants were in a resting state with their eyes closed. The data collection process included rigorous quality control measures to ensure data accuracy and consistency. The dataset contains recordings of 36 Alzheimer’s patients, 23 frontotemporal dementia patients, and 29 healthy age-matched subjects. For each subject, the Mini-Mental State Examination score is reported. A monopolar montage was used to collect the signals. A raw and preprocessed EEG is included in the standard BIDS format. For the preprocessed signals, established methods such as artifact subspace reconstruction and an independent component analysis have been employed for denoising. The dataset has significant reuse potential since Alzheimer’s EEG Machine Learning studies are increasing in popularity and there is a lack of publicly available EEG datasets. The resting-state EEG data can be used to explore alterations in brain activity and connectivity in these conditions, and to develop new diagnostic and treatment approaches. Additionally, the dataset can be used to compare EEG characteristics between different types of dementia, which could provide insights into the underlying mechanisms of these conditions.

Two sides of the same coin: Kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. A tutorial

A tutorial is presented on the operation and properties of the non-linear multivariate regression model kernel partial least-squares (KPLS). After the discussion of a simple non-linear univariate problem, solved by regressing a dependent variable on the projection of an independent variable onto a set of Gaussian functions, the principles of KPLS are introduced for processing non-linear multivariate data. The following aspects are covered: (1) the estimation of the model sensitivity as a function of analyte concentration from error propagation concepts, (2) the proposal of a parameter measuring the degree of non-linearity, to avoid a black-and-white description of data sets as either linear or non-linear, (3) the use of the model parameters for variable selection. The application of KPLS to both simulated and experimental data sets is discussed, in the latter case involving near infrared spectra employed for the determination of quality parameters in foodstuff samples and fluorescence spectroscopic data for the study of systems of biological relevance. Computer codes written in the popular MATLAB and R environments are also provided.

A national seismic risk model for Canada: Methodology and scientific basis

Canada is exposed to rare but potentially destructive earthquakes that threaten densely settled metropolitan centers in many parts of the country. To assess the impacts and consequences of future natural-hazard events and help advance policy goals and objectives of the Sendai Framework for Disaster Risk Reduction, Natural Resources Canada, through a collaborative partnership with the Global Earthquake Model Foundation, produced a national seismic risk model. Developing this model has required the creation of a national exposure inventory, Canadian-specific fragility and vulnerability curves, and significant simplification of the Canadian Seismic Hazard Model which forms the basis for the design seismic hazard values of the National Building Code of Canada. Using the Global Earthquake Model Foundation’s OpenQuake Engine, probabilistic stochastic risk modeling is completed under baseline and simulated retrofit conditions to assess seismic risk at the neighborhood level for all settled areas in Canada. Output risk metrics include the expected immediate physical impacts of earthquake events such as building damage, casualties, and direct economic losses. This article documents the technical details of the modeling approach including a description of novel data sets in use, a summary of the extensive sensitivity testing undertaken, and characterization of quality control implemented in the absence of usable validating earthquake loss data. The results from this model, such as loss exceedance curves and annual average losses, provide an open, accessible and quantitative base of evidence for decision-making at local, regional, and national levels. As a large country with a complex seismic hazard model and dispersed populations, this Canadian study is unique. However, the challenges faced and solutions offered are likely to be of interest to other nations pursuing similar programs.

Metadata implementation and data discoverability: A survey on university libraries' Dataverse portals

The purpose of this practical case study is to examine the development of Dataverse, a global research data management consortium. This paper is the second in a project focusing on data discoverability and current metadata implementation on the Dataverse portals established by 27 university libraries worldwide. Five research questions were proposed to identify the most popular metadata standards and elements, search interface options, and result display formats by those portals. The data were collected from 27 university libraries worldwide between December 1, 2020 and January 31, 2021. According to the results of the descriptive analyses, the most popular metadata elements for the dataset overview were Subject and Description, while Dataset persistent ID, Publication Date, Title, Author, Contact, Deposit Date, Depositor, Description, and Subject were the most popular elements for the metadata record of each dataset. Publication Year, Author Names, and Subject were found to be the most common search facets used by the portals. English was the most common language used for the search interfaces and metadata descriptions. Based on their findings from this evidence-based study, the authors recommend future research on the development of institutional data portal infrastructure, on stakeholder outreach and training, and on user studies on dataset retrieval.

GIR dataset: A geometry and real impulse response dataset for machine learning research in acoustics

Acoustics play a significant role in our everyday lives, influencing our communication, well-being, and perception of space. Fast and precise acoustics simulation is crucial for the accurate design of real spaces by architects and acousticians and maximises the user’s immersion in virtual and augmented reality environments. Computer simulation techniques can help to simulate and analyse acoustics. However, their cumbersome, computationally expensive, and often inaccurate results discourage most architecture practices from including acoustic evaluation in their design workflow and prevent real-time accurate audio synthesis in virtual reality. Recent advancements in Machine Learning (ML) and particularly Deep Learning offer compelling solutions to address the above problems. ML methods require large datasets for training, and existing datasets are either not large enough, contain synthetic data, or are not suitable for room acoustics research. This paper presents the GIR Dataset, a dataset of 920’712 real Impulse Responses (IRs) of 312 architectural geometries for the study of early reflections from diffusive surfaces. The paper provides a detailed description of the GIR Dataset’s content and an ML use-case example. The dataset and the code described in this paper are open-sourced.

Multiclass Support Vector Data Description in Extreme Learning Machine Feature Space

Support vector data description (SVDD) method aims to address the one-class classification (OCC) problem to find a hypersphere-shaped description of target data set. For extending SVDD to multiclass classification while remaining the ability of detecting outliers, we propose a novel multiclass SVDD scheme which can be used in effective feature mapping and meta-class separation based on the extreme learning machine algorithm (ELM-MSVDD). Accordingly, the imprecise data difficult to distinguish in specific classes is classified to a meta-class,the meta-class is defined by the disjunction of these specific classes, this operation can reduce the error rate effectively. Experimental results of our ELM-MSVDD method show well performance on the datasets from the UCI machine learning library and radar signal source recognition. Meanwhile, our proposed method provide a theoretical and practical support for other relevant pattern recognition field.

Customer Churn Prediction Based on the Decision Tree and Random Forest Model

The rate at which customers discontinue utilizing a company's services during a predetermined time period is known as the customer churn rate, also known as the attrition rate. Hence, developing a prediction model to predict the potential churn customers will generate an early alert for the company to provide them with better service. This study is divided into two main parts: dealing with a dataset about customer behaviors in a bank and building churn prediction models using machine learning algorithms. The data preprocessing part includes dataset description and some adjustments on original dataset to make it accessible for analysis, including deleting unimportant feature and adjusting feature names. Then the study apportions the modified dataset into train set and test set with an 80-20 split. Next, the study imports two kinds of machine learning algorithms, random forest classifier and decision tree classifier, to build churn prediction models. In each model, the study first performs feature selections and visualizes feature importance in bar graphs. Then the study tests each model on testing set and visualizes model performances using confusion matrices and accuracy scores. The results show that both models get most predictions correct while random forest model has a better performance due to its higher accuracy score of 91%.

Still a “spectator”? Capabilities of the Spanish REPER and Spain’s influence in the Council of the EU

To what extent is the Spanish Permanent Representation to the EU comparable to other MS in terms of capabilities? What are the indications of Spain’s strengths and weaknesses in EU legislative processes? This article investigates the resources mobilized by Spain as part of the EU policymaking processes in Brussels and its influence in shaping decision outcomes. Drawing on new qualitative and descriptive quantitative data sets, this research compares the human resources of the Spanish Permanent Representation, its internal coordination process, and its external engagement with EU stakeholders, to other member states. The article highlights possible implications of these variations for Spain’s bargaining success in the Council of the EU. The findings reveal the challenges that Spanish negotiators face in exerting influence in the EU decision-making process and show how adequate levels of administrative and human resources are sometimes not sufficient for Spain to leave the group of “spectator” member states in the governance of the EU.

Artificial Intelligence for the Classification of Pigmented Skin Lesions in Populations with Skin of Color: A Systematic Review

Background: While skin cancers are less prevalent in people with skin of color, they are more often diagnosed at later stages and have a poorer prognosis. The use of artificial intelligence (AI) models can potentially improve early detection of skin cancers; however, the lack of skin color diversity in training datasets may only widen the pre-existing racial discrepancies in dermatology. Objective: The aim of this study was to systematically review the technique, quality, accuracy, and implications of studies using AI models trained or tested in populations with skin of color for classification of pigmented skin lesions. Methods: PubMed was used to identify any studies describing AI models for classification of pigmented skin lesions. Only studies that used training datasets with at least 10% of images from people with skin of color were eligible. Outcomes on study population, design of AI model, accuracy, and quality of the studies were reviewed. Results: Twenty-two eligible articles were identified. The majority of studies were trained on datasets obtained from Chinese (7/22), Korean (5/22), and Japanese populations (3/22). Seven studies used diverse datasets containing Fitzpatrick skin type I–III in combination with at least 10% from black Americans, Native Americans, Pacific Islanders, or Fitzpatrick IV–VI. AI models producing binary outcomes (e.g., benign vs. malignant) reported an accuracy ranging from 70% to 99.7%. Accuracy of AI models reporting multiclass outcomes (e.g., specific lesion diagnosis) was lower, ranging from 43% to 93%. Reader studies, where dermatologists’ classification is compared with AI model outcomes, reported similar accuracy in one study, higher AI accuracy in three studies, and higher clinician accuracy in two studies. A quality review revealed that dataset description and variety, benchmarking, public evaluation, and healthcare application were frequently not addressed. Conclusions: While this review provides promising evidence of accurate AI models in populations with skin of color, the majority of the studies reviewed were obtained from East Asian populations and therefore provide insufficient evidence to comment on the overall accuracy of AI models for darker skin types. Large discrepancies remain in the number of AI models developed in populations with skin of color (particularly Fitzpatrick type IV–VI) compared with those of largely European ancestry. A lack of publicly available datasets from diverse populations is likely a contributing factor, as is the inadequate reporting of patient-level metadata relating to skin color in training datasets.

Classification and Segmentation of Diabetic Retinopathy: A Systemic Review

Diabetic retinopathy (DR) is a major reason of blindness around the world. The ophthalmologist manually analyzes the morphological alterations in veins of retina, and lesions in fundus images that is a time-taking, costly, and challenging procedure. It can be made easier with the assistance of computer aided diagnostic system (CADs) that are utilized for the diagnosis of DR lesions. Artificial intelligence (AI) based machine/deep learning methods performs vital role to increase the performance of the detection process, especially in the context of analyzing medical fundus images. In this paper, several current approaches of preprocessing, segmentation, feature extraction/selection, and classification are discussed for the detection of DR lesions. This survey paper also includes a detailed description of DR datasets that are accessible by the researcher for the identification of DR lesions. The existing methods limitations and challenges are also addressed, which will assist invoice researchers to start their work in this domain.

Code4ML: a large-scale dataset of annotated Machine Learning code.

The use of program code as a data source is increasingly expanding among data scientists. The purpose of the usage varies from the semantic classification of code to the automatic generation of programs. However, the machine learning model application is somewhat limited without annotating the code snippets. To address the lack of annotated datasets, we present the Code4ML corpus. It contains code snippets, task summaries, competitions, and dataset descriptions publicly available from Kaggle-the leading platform for hosting data science competitions. The corpus consists of ~2.5 million snippets of ML code collected from ~100 thousand Jupyter notebooks. A representative fraction of the snippets is annotated by human assessors through a user-friendly interface specially designed for that purpose. Code4ML dataset can help address a number of software engineering or data science challenges through a data-driven approach. For example, it can be helpful for semantic code classification, code auto-completion, and code generation for an ML task specified in natural language.

Using Ontologies to Create Machine-Actionable Datasets: Two Case Studies

Achieving the highest levels of compliance with the FAIR (findable, accessible, interoperable, reusable) principles for scientific data management and stewardship requires machine-actionable semantic representations of data and metadata. Human and machine interpretation and reuse of measurement datasets rely on metrological information that is often specified inconsistently or cannot be inferred automatically, while several ontologies to capture the metrological information are available, practical implementation examples are few. This work aims to close this gap by discussing how standardised measurement data and metadata could be presented using semantic web technologies. The examples provided in this paper are machine-actionable descriptions of Earth observation and bathymetry measurement datasets, based on two ontologies of quantities and units of measurement selected for their prominence in the semantic web. The selected ontologies demonstrated a good coverage of the concepts related to quantities, dimensions, and individual units as well as systems of units, but showed variations and gaps in the coverage, completeness and traceability of other metrology concept representations such as standard uncertainty, expanded uncertainty, combined uncertainty, coverage factor, probability distribution, etc. These results highlight the need for both (I) user-friendly tools for semantic representations of measurement datasets and (II) the establishment of good practices within each scientific community. Further work will consequently investigate how to support ontology modelling for measurement uncertainty and associated concepts.

Shared or Self-rule? Regional Legislative Initiatives in Multi-level Spain, 1979-2021

ABSTRACT This paper examines regional legislative initiatives in Spain, a mechanism of shared-rule regulated in article 87.2 of the Spanish Constitution. Through description and analysis of an original dataset covering all legislative terms from 1978 to 2021, it is shown how this specific mechanism has not accomplished its shared-rule objective. Moreover, the article identifies patterns that determine the strategic use, intensity and failure or success of the legislative initiatives. We find diverging trends across regions exemplified by Catalonia, the most active territory but with a very low approval rate. Overall, the analysis underlines how the state-wide scope initiatives seem to have a strategic rather than a legislative purpose while, on the other hand, regional scope initiatives are explained by minor self-rule objectives.

Language-Based Image Manipulation Built on Language-Guided Ranking

Text-based image manipulation is a popular subject and has many applications. However, it is a challenging task because there is no ground-truth edited dataset and textual descriptions have abstractive and ambiguous properties. To alleviate the difficult issues, we propose a manipulation framework consisting of the proposal attentional GANs, language-related semantic mask, and language-guided ranker. Specially, we construct an editing proposal generator to generate the suitable edited proposals with and without semantic conditions, which supports the reorganization of sub-generators to output proposals in various aspects as many as possible. To distinguish the text-relevant and the text-irrelevant regions, we introduce a language-related semantic mask based on the source image and target caption. Then, we exploit a language-guided ranker to retrieve the best edited result from the edited proposals through using the multi-modal similarity and the language-related semantic mask. Extensive experiments on widely-used datasets demonstrate that our model could manipulate images interactively and improve the editing quality effectively.

Supplementary material

Detailed description of data set of eight German food retailers/groups: Table of scources and assignment to index cards