ARTIFICIAL DATA GENERATION FOR ONE-CLASS CLASSIFICATION - A Case Study of Dimensionality Reduction for Text and Biological Data

2009 ◽  
Keyword(s):  
Dimensionality Reduction ◽  
Biological Data ◽  
Data Generation ◽  
Artificial Data ◽  
One Class Classification

scholarly journals MODEL-BASED DESIGN OF AM COMPONENTS TO ENABLE DECENTRALIZED DIGITAL MANUFACTURING SYSTEMS

2021 ◽  
Vol 1 ◽  
pp. 2127-2136
Author(s):  
Olivia Borgue ◽  
John Stavridis ◽  
Tomas Vannucci ◽  
Panagiotis Stavropoulos ◽  
Harry Bikas ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
Manufacturing Systems ◽  
Production Systems ◽  
Data Generation ◽  
Production Networks ◽  
Model Based ◽  
Manufacturing Technologies ◽  
Am Processes ◽  
Final Consumer

AbstractAdditive manufacturing (AM) is a versatile technology that could add flexibility in manufacturing processes, whether implemented alone or along other technologies. This technology enables on-demand production and decentralized production networks, as production facilities can be located around the world to manufacture products closer to the final consumer (decentralized manufacturing). However, the wide adoption of additive manufacturing technologies is hindered by the lack of experience on its implementation, the lack of repeatability among different manufacturers and a lack of integrated production systems. The later, hinders the traceability and quality assurance of printed components and limits the understanding and data generation of the AM processes and parameters. In this article, a design strategy is proposed to integrate the different phases of the development process into a model-based design platform for decentralized manufacturing. This platform is aimed at facilitating data traceability and product repeatability among different AM machines. The strategy is illustrated with a case study where a car steering knuckle is manufactured in three different facilities in Sweden and Italy.

scholarly journals Práticas de letramento e whatsapp: estudo de caso no contexto de português como língua de acolhimento, à luz da perspectiva ecológica

2021 ◽  
Vol 2 (3) ◽  
pp. 218-237
Author(s):  
Rosyanne Louise Autran Lourenço ◽  
Eliana Barbosa dos Santos
Keyword(s):  
Learning Process ◽  
Literacy Practices ◽  
Qualitative Case Study ◽  
Participant Observation ◽  
Ecological Perspective ◽  
Data Generation ◽  
Field Notes ◽  
Teaching Learning ◽  
Refugee Immigrants

Este artigo visa a apresentar, sob uma perspectiva ecológica de letramento, resultados da análise de práticas sociodiscursivas do processo de ensino-aprendizagem de Português Língua de Acolhimento, de imigrantes refugiados no Brasil, realizadas por meio do WhatsApp. Teoricamente, o estudo circunscreve-se às dimensões analíticas de letramento (MOREAU et al., 2013), sob a perspectiva ecológica dos estudos linguísticos (VAN LIER, 2004, 2010), fundamentando-se em pressupostos referentes aos recursos multimodais das tecnologias digitais (LEFFA, 2006; MORAN, 2013) e à função mediadora da linguagem (VIGOTSKI, 1971), em especial, do Português Língua de Acolhimento (BARBOSA; SÃO BERNARDO, 2017) e de suas implicações referentes à noção de afetividade (LEITE, 2012). Metodologicamente, trata-se de estudo qualitativo de caso (STAKE, 1994), de base etnográfica virtual (SANTOS; GOMES, 2013) cuja geração dos dados ocorreu por meio de observação participante (BOGDAN; BIKLEN, 1998) e notas de campo (FETTERMAN, 1998). Sua relevância reside na urgência no processo de imersão de imigrantes refugiados em práticas sociodiscursivas que viabilizem a obtenção de condições mínimas de vida digna e a garantia de autonomia em sua agência no país de destino (COSTA; TAÑO, 2018). Os resultados da pesquisa sugerem que a abordagem ecológica de práticas de letramento em ambiente virtual amplia a compreensão das articulações inerentes ao processo de ensino-aprendizagem de línguas, propiciando ao docente melhores condições de promover a autonomia dos estudantes, em contexto de imigração, na condução de soluções que atendam às suas necessidades mais prementes, voltadas para as práticas sociais de imersão no país de chegada.   This article aims to present, in the light of an ecological perspective of literacy, the results of the analysis of sociodiscursive practices of the teaching-learning process of Portuguese as a Host Language, through WhatsApp by refugee immigrants in Brazil. Theoretically, the study is limited to the ecological perspective of linguistic studies (VAN LIER, 2004, 2010) and analytical literacy dimensions (MOREAU ET AL., 2013) based on assumptions regarding the multimodal resources of digital technologies (LEFFA, 2006; MORAN, 2013) and the mediating function of language (VIGOTSKI, 2009) in particular the Portuguese Host Language (BARBOSA; SÃO BERNARDO, 2017) and its implications regarding the notion of affectivity (LEITE, 2012). Methodologically, it is a qualitative case study (STAKE, 1994) with a virtual ethnographic basis (SANTOS; GOMES, 2013) whose data generation occurred through participant observation (BOGDAN; BIKLEN, 1998) and field notes (FETTERMAN, 1998). Its relevance resides in the urgency in the process of refugee immigrants sociodiscursive practices that make it possible to obtain minimum conditions of dignified life and guarantee autonomy at their agency in the destination country (COSTA; TAÑO, 2018). The research results suggest that the ecological approach to literacy practices in a virtual environment broadens the understanding of the articulations inherent to the language teaching-learning process, providing the teacher better conditions to promote the autonomy of the students in the context of immigration, in driving solutions that meet their pressing sociodiscursive needs, focused on social immersion practices in the country of arrival.

Capturing discrete latent structures: choose LDs over PCs

Biostatistics ◽  
2021 ◽  
Author(s):  
Theresa A Alexander ◽  
Rafael A Irizarry ◽  
Héctor Corrada Bravo
Keyword(s):  
Dimensionality Reduction ◽  
Biological Data ◽  
Reduction Technique ◽  
Latent Structure ◽  
High Dimensional ◽  
Underlying Structure ◽  
Linear Transformations ◽  
Latent Structures ◽  
Low Dimensional ◽  
Discriminatory Information

Summary High-dimensional biological data collection across heterogeneous groups of samples has become increasingly common, creating high demand for dimensionality reduction techniques that capture underlying structure of the data. Discovering low-dimensional embeddings that describe the separation of any underlying discrete latent structure in data is an important motivation for applying these techniques since these latent classes can represent important sources of unwanted variability, such as batch effects, or interesting sources of signal such as unknown cell types. The features that define this discrete latent structure are often hard to identify in high-dimensional data. Principal component analysis (PCA) is one of the most widely used methods as an unsupervised step for dimensionality reduction. This reduction technique finds linear transformations of the data which explain total variance. When the goal is detecting discrete structure, PCA is applied with the assumption that classes will be separated in directions of maximum variance. However, PCA will fail to accurately find discrete latent structure if this assumption does not hold. Visualization techniques, such as t-Distributed Stochastic Neighbor Embedding (t-SNE) and Uniform Manifold Approximation and Projection (UMAP), attempt to mitigate these problems with PCA by creating a low-dimensional space where similar objects are modeled by nearby points in the low-dimensional embedding and dissimilar objects are modeled by distant points with high probability. However, since t-SNE and UMAP are computationally expensive, often a PCA reduction is done before applying them which makes it sensitive to PCAs downfalls. Also, tSNE is limited to only two or three dimensions as a visualization tool, which may not be adequate for retaining discriminatory information. The linear transformations of PCA are preferable to non-linear transformations provided by methods like t-SNE and UMAP for interpretable feature weights. Here, we propose iterative discriminant analysis (iDA), a dimensionality reduction technique designed to mitigate these limitations. iDA produces an embedding that carries discriminatory information which optimally separates latent clusters using linear transformations that permit post hoc analysis to determine features that define these latent structures.

GRASP with Path-Relinking for Data Clustering: A Case Study for Biological Data

2011 ◽  
pp. 410-420 ◽  
Author(s):  
Rafael M. D. Frinhani ◽  
Ricardo M. A. Silva ◽  
Geraldo R. Mateus ◽  
Paola Festa ◽  
Mauricio G. C. Resende
Keyword(s):  
Data Clustering ◽  
Biological Data ◽  
Path Relinking

<i>Quantifying agricultural data generation on Wisconsin farms: A case study</i>

2018 ◽  
Author(s):  
Jessica L Drewry ◽  
Brian D Luck ◽  
John M Shutske ◽  
David D Trechter
Keyword(s):  
Data Generation

A case study for block-based linked data generation: Recipes as jigsaw puzzles

2019 ◽  
Vol 46 (3) ◽  
pp. 419-433 ◽  
Author(s):  
Övünç Öztürk ◽  
Tuğba Özacar
Keyword(s):  
Linked Data ◽  
Heterogeneous Systems ◽  
Data Repository ◽  
Data Generation ◽  
Text Input ◽  
Ontology Language ◽  
Data Generator ◽  
System Usability Scale ◽  
The Masses

This article is a proof-of-concept case study to evaluate the functionality of a block metaphor–based linked data generator. In this work, we chose to produce linked data repository of recipes, which provide a medium for people to share their regional and healthy recipes with the masses. However, the same approach can also be adapted easily to other domains. Therefore, the applicability of our approach extends well beyond the food domain that we are considering in this article. As a medium for information sharing and understanding between heterogeneous systems, ontologies will play an important role in the realisation of the Internet of things (IoT) vision. Therefore, an ontology-based recipe repository would also be one of the basic blocks of a smart kitchen environment. However, building ontologies is a challenging task, especially for users who are not conversant in the ontology building languages. This article proposes an approach that can be used even by non-experts and facilitates the sharing and searching of recipe data. In our case, we exploit the features of the block paradigm to publish recipes in Linked Data format. In this way, users do not have to know the OWL (Web Ontology Language) syntax and the text input is kept minimal. As far as we know, this article is the first study that produces linked data using Blockly in the literature. We also conducted a user-based evaluation of the proposed approach using the System Usability Scale (SUS) questionnaire.

Sign in / Sign up

Export Citation Format

Share Document