Search results for "UHI"
showing 10 items of 157 documents
Data-driven decision support to reduce "driving-under the influence of alcohol" offenses
2018
Extracting valuable knowledge from data to support decision making is a widely practiced trend. Data-driven decision support (DDDS) provides insight for decision makers by exploring and extracting underlying patterns within a dataset. This thesis covers the process of DDDS in reducing driving under the influence of alcohol (DUI) offenses by introducing proposed prison sentences. In this thesis, DDDS is applied to a DUI dataset by analyzing patterns in the dataset and by introducing proposed prison sentences for offenders to reduce the number of DUI cases. Background theories in data mining, machine learning, optimization and decision science that are related to the thesis project are also c…
A First Experiment on Including Text Literals in KGloVe
2018
Graph embedding models produce embedding vectors for entities and relations in Knowledge Graphs, often without taking literal properties into account. We show an initial idea based on the combination of global graph structure with additional information provided by textual information in properties. Our initial experiment shows that this approach might be useful, but does not clearly outperform earlier approaches when evaluated on machine learning tasks.
Classification of Heart Sounds Using Convolutional Neural Network
2020
Heart sounds play an important role in the diagnosis of cardiac conditions. Due to the low signal-to-noise ratio (SNR), it is problematic and time-consuming for experts to discriminate different kinds of heart sounds. Thus, objective classification of heart sounds is essential. In this study, we combined a conventional feature engineering method with deep learning algorithms to automatically classify normal and abnormal heart sounds. First, 497 features were extracted from eight domains. Then, we fed these features into the designed convolutional neural network (CNN), in which the fully connected layers that are usually used before the classification layer were replaced with a global averag…
Comparison of Internal Clustering Validation Indices for Prototype-Based Clustering
2017
Clustering is an unsupervised machine learning and pattern recognition method. In general, in addition to revealing hidden groups of similar observations and clusters, their number needs to be determined. Internal clustering validation indices estimate this number without any external information. The purpose of this article is to evaluate, empirically, characteristics of a representative set of internal clustering validation indices with many datasets. The prototype-based clustering framework includes multiple, classical and robust, statistical estimates of cluster location so that the overall setting of the paper is novel. General observations on the quality of validation indices and on t…
Agroecosystems shape population genetic structure of the greenhouse whitefly in Northern and Southern Europe
2014
International audience; Background: To predict further invasions of pests it is important to understand what factors contribute to the genetic structure of their populations. Cosmopolitan pest species are ideal for studying how different agroecosystems affect population genetic structure within a species at different climatic extremes. We undertook the first population genetic study of the greenhouse whitefly (Trialeurodes vaporariorum), a cosmopolitan invasive herbivore, and examined the genetic structure of this species in Northern and Southern Europe. In Finland, cold temperatures limit whiteflies to greenhouses and prevent them from overwintering in nature, and in Greece, milder tempera…
Data Analytics in Healthcare: A Tertiary Study
2022
AbstractThe field of healthcare has seen a rapid increase in the applications of data analytics during the last decades. By utilizing different data analytic solutions, healthcare areas such as medical image analysis, disease recognition, outbreak monitoring, and clinical decision support have been automated to various degrees. Consequently, the intersection of healthcare and data analytics has received scientific attention to the point of numerous secondary studies. We analyze studies on healthcare data analytics, and provide a wide overview of the subject. This is a tertiary study, i.e., a systematic review of systematic reviews. We identified 45 systematic secondary studies on data analy…
Talent identification in soccer using a one-class support vector machine
2019
Abstract Identifying potential future elite athletes is important in many sporting events. The successful identification of potential future elite athletes at an early age would help to provide high-quality coaching and training environments in which to optimize their development. However, a large variety of different skills and qualities are needed to succeed in elite sports, making talent identification generally a complex and multifaceted problem. Due to the rarity of elite athletes, datasets are inherently imbalanced, making classical statistical inference difficult. Therefore, we approach talent identification as an anomaly detection problem. We trained a nonlinear one-class support ve…
Reconsidering authorship in the Ciceronian corpus through computational authorship attribution
2019
In recent years, methods of computational authorship attribution have offered promising results for the reattribution of classical texts. We use and further develop these methods to verify the authorship of several texts belonging or related to the Ciceronian corpus: Rhetorica ad C. Herennium, De inventione, De optimo genere oratorum, and Commentariolum petitionis. We use two classifiers, Support Vector Machine and Convolutional Neural Network, of which the latter is more accurate except in regard to certain aspects of vocabulary. The most important of our results is that Commentariolum petitionis seems to be authored by Marcus Cicero, not by his brother Quintus. Negli ultimi anni metodi co…
Haavoittuvuuden kudelmat : digitaalinen subjekti ja haavoittuvuus datavetoista yhteiskuntaa käsittelevässä tutkimuskirjallisuudessa
2021
Artikkelissa tarkastellaan sitä, millaisia merkityksiä haavoittuvuudelle on annettu datavetoista yhteiskuntaa ja digitaalista subjektia koskevassa tutkimuskirjallisuudessa. Artikkeli perustuu kirjallisuuskatsaukseen, joka on tehty vuosina 2015–2020 ilmestyneistä haavoittuvuutta datafikaation kontekstissa käsittelevistä tieteellisistä julkaisuista. Kirjallisuushaut tehtiin yhteiskuntatieteiden alojen keskeisistä tietokannoista ja digitaalisista kirjastoista. Hakujen pohjalta tutkimuskirjallisuus järjestettiin neljään teemakokonaisuuteen: 1) datavalvonnan tuottamat haavoittuvuudet, 2) data tietämisen tapana ja osallisuutena, 3) digitaalisten subjektien kategorisointi ja näkyvyyden säätely sek…
Textiles in blue : production, consumption and material culture in rural areas in early-nineteenth century Finland
2021
The article focuses on masculine consumption patterns and the production and dyeing of textiles in rural Finland in the early nineteenth century. It maintains that the rural consumption of textiles as well as individual choices and tastes evolved, and our selected examples of males’ wardrobes demonstrate that contemporary styles were followed. The article targets an era that can be regarded as a watershed: this was a time when mass production was in its infancy and craft production and self-sufficiency were still relevant to household economies. As the wealth of certain groups, particularly landed peasantry, increased, they began among other things to purchase and wear clothes dyed with imp…