Journal articles: 'Data representation'

1

Frederick, Karen, Lucy Barnard-Brak, and Tracey Sulak. "Under-representation in nationally representative secondary data." International Journal of Research & Method in Education 35, no. 1 (April 2012): 31–40. http://dx.doi.org/10.1080/1743727x.2011.609545.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Yusriyah, Yais, and Mega Achdisty Noordyana. "Kemampuan Representasi Matematis Siswa SMP pada Materi Penyajian Data di Desa Bungbulang." Plusminus: Jurnal Pendidikan Matematika 1, no. 1 (March 31, 2021): 47–60. http://dx.doi.org/10.31980/plusminus.v1i1.1025.

Full text

Abstract:

Several studies have shown that students' mathematical representation skills are still low. The research objective was to analyze the mathematical representation ability of junior high school students on data presentation material. The research was conducted in Citalahab Kaler Village, Bungbulang-Garut Village. This research uses a qualitative approach. The method used is the descriptive analysis method, which involved 3 students as a sample, using a simple random sampling technique. The test instrument for the students' mathematical representation ability consisted of 5 questions in the form of descriptions. The results of the study are (1) The ability of mathematical representations on the pictorial representation indicator is that almost all students from the three samples have been able to solve a problem using a visual representation. (2) The ability of mathematical representation in the symbolic representation indicator is that almost all students from the three samples have not been able to solve problems using symbolic representations. (3) The ability of mathematical representation on the verbal representation indicator is that some students can use verbal representations, but some of them are still unable to convey their mathematical ideas in their language.

APA, Harvard, Vancouver, ISO, and other styles

3

Mishra, Sandip. "Analytical Data Representation." International Journal of Computer Sciences and Engineering 7, no. 11 (November 30, 2019): 68–72. http://dx.doi.org/10.26438/ijcse/v7i11.6872.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Hawkins, Peter, Alex Aiken, Kathleen Fisher, Martin Rinard, and Mooly Sagiv. "Data representation synthesis." ACM SIGPLAN Notices 47, no. 6 (August 6, 2012): 38. http://dx.doi.org/10.1145/2345156.1993504.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Hawkins, Peter, Alex Aiken, Kathleen Fisher, Martin Rinard, and Mooly Sagiv. "Data representation synthesis." ACM SIGPLAN Notices 46, no. 6 (June 4, 2011): 38–49. http://dx.doi.org/10.1145/1993316.1993504.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Lestari, Nurcholif Diah Sri, Wasilatul Murtafiah, Marheny Lukitasari, Suwarno Suwarno, and Inge Wiliandani Setya Putri. "IDENTIFIKASI RAGAM DAN LEVEL KEMAMPUAN REPRESENTASI PADA DESAIN MASALAH LITERASI MATEMATIS DARI MAHASISWA CALON GURU." KadikmA 13, no. 1 (April 30, 2022): 11. http://dx.doi.org/10.19184/kdma.v13i1.31538.

Full text

Abstract:

Representation is one of the fundamental abilities of mathematics reflected by students understanding of mathematics concepts, principles, or procedures, so it becomes crucial for teachers to develop students' mathematical representation skills. This research was time to describe the representation used in the problem and the level of mathematical representation ability needed to solve mathematical literacy problems. The data was collected through the assignment to design mathematical literacy problems between 3-10 pieces and interview as triangulation on 35 prospective elementary school teacher students. The data are grouped based on various representations and analyzed quantitatively and descriptively. Then one problem is chosen randomly for each type of representation to describe the level of representation ability needed to solve the problem qualitatively. The results show that the mathematical representations used in designed mathematical literacy problems are pictorial-verbal, pictorial-symbolic, verbal-symbolic, pictorial, verbal, symbolic, and pictorial-verbal-symbolic representations. The level of representational ability that tends to be needed to solve problems is levels 0 and 1. This study suggests that prospective teacher students should develop mathematical representation knowledge to improve the quality of their learning in the future

APA, Harvard, Vancouver, ISO, and other styles

7

Kadi, Hafid, Mohammed Rebbah, Boudjelal Meftah, and Olivier Lézoray. "A Data Representation Model for Personalized Medicine." International Journal of Healthcare Information Systems and Informatics 16, no. 4 (October 2021): 1–25. http://dx.doi.org/10.4018/ijhisi.295822.

Full text

Abstract:

Personalized medicine exploits the patient data, for example, genetic compositions, and key biomarkers. During the data mining process, the key challenges are the information loss, the data types heterogeneity and the time series representation. In this paper, a novel data representation model for personalized medicine is proposed in light of these challenges. The proposed model will account for the structured, temporal and non-temporal data and their types, namely, numeric, nominal, date, and Boolean. After the "Date and Boolean" data transformation, the nominal data are treated by dispersion while several clustering techniques are deployed to control the numeric data distribution. Ultimately, the transformation process results in three homogeneous representations with these representations having only two dimensions to ease the exploration of the represented dataset. Compared to the Symbolic Aggregate Approximation technique, the proposed model preserves the time-series information, conserves as much data as possible and offers multiple simple representations to be explored.

APA, Harvard, Vancouver, ISO, and other styles

8

Ott, Frédéric, and Sergey Kozhevnikov. "Off-specular data representations in neutron reflectivity." Journal of Applied Crystallography 44, no. 2 (February 11, 2011): 359–69. http://dx.doi.org/10.1107/s0021889811002858.

Full text

Abstract:

The different methods of data acquisition and representation in neutron reflectometry measurements are discussed. The different representations of diffuse scattering are compared and the off-specular features that can be observed in neutron reflectivity are described. The representation of diffuse data in the `natural' reciprocal-space coordinates (Qx, Qz) leads to a loss of information for smallQzscattering vector. It is suggested that an intermediate representation (Qx/Qz, Qz) allows the unification of data measured on different types of spectrometers and permits a straightforward comparison and understanding while keeping all the interesting features of the off-specular scattering. The discussion is illustrated by diffuse scattering data measured on neutron waveguides obtained on both fixed-wavelength and time-of-flight spectrometers. A simple procedure allowing for dense remapping between different representations is described.

APA, Harvard, Vancouver, ISO, and other styles

9

Corcoran, Padraig, and Irena Spasić. "Self-Supervised Representation Learning for Geographical Data—A Systematic Literature Review." ISPRS International Journal of Geo-Information 12, no. 2 (February 12, 2023): 64. http://dx.doi.org/10.3390/ijgi12020064.

Full text

Abstract:

Self-supervised representation learning (SSRL) concerns the problem of learning a useful data representation without the requirement for labelled or annotated data. This representation can, in turn, be used to support solutions to downstream machine learning problems. SSRL has been demonstrated to be a useful tool in the field of geographical information science (GIS). In this article, we systematically review the existing research literature in this space to answer the following five research questions. What types of representations were learnt? What SSRL models were used? What downstream problems were the representations used to solve? What machine learning models were used to solve these problems? Finally, does using a learnt representation improve the overall performance?

APA, Harvard, Vancouver, ISO, and other styles

10

Vrotsou, Katerina, Camilla Forsell, and Matthew Cooper. "2D and 3D Representations for Feature Recognition in Time Geographical Diary Data." Information Visualization 9, no. 4 (December 3, 2009): 263–76. http://dx.doi.org/10.1057/ivs.2009.30.

Full text

Abstract:

Time geographical representations are becoming a common approach to analysing spatio-temporal data. Such representations appear intuitive in the process of identifying patterns and features as paths of populations form tracks through the 3D space, which can be seen converging and diverging over time. In this article, we compare 2D and 3D representations within a time geographical visual analysis tool for activity diary data. We identify a representative task and evaluate task performance between the two representations. The results show that the 3D representation has benefits over the 2D representation for feature identification but also indicate that these benefits can be lost if the 3D representation is not carefully constructed to help the user to see them.

APA, Harvard, Vancouver, ISO, and other styles

11

Coffey, Amanda, Holbrook Beverley, and Atkinson Paul. "Qualitative Data Analysis: Technologies and Representations." Sociological Research Online 1, no. 1 (March 1996): 80–91. http://dx.doi.org/10.5153/sro.1.

Full text

Abstract:

In this paper we address a number of contemporary themes concerning the analysis of qualitative data and the ethnographic representation of social realities. A contrast is drawn. On the one hand, a diversity of representational modes and devices is currently celebrated, in response to various critiques of conventional ethnographic representation. On the other hand, the widespread influence of computer- assisted qualitative data analysis is promoting convergence on a uniform mode of data analysis and representation (often justified with reference to grounded theory). We note the ironic contrast between these two tendencies, the heterodox and the orthodox, in contemporary qualitative research. We go on to suggest that there exist alternatives that reflect both the diversity of representational approaches, and the broader possibilities of contemporary computing. We identify the technical and intellectual possibilities of hypertext software as offering just one such synthesis.

APA, Harvard, Vancouver, ISO, and other styles

12

Ye, Zhonglin, Haixing Zhao, Ke Zhang, Yu Zhu, and Zhaoyang Wang. "An Optimized Network Representation Learning Algorithm Using Multi-Relational Data." Mathematics 7, no. 5 (May 21, 2019): 460. http://dx.doi.org/10.3390/math7050460.

Full text

Abstract:

Representation learning aims to encode the relationships of research objects into low-dimensional, compressible, and distributed representation vectors. The purpose of network representation learning is to learn the structural relationships between network vertices. Knowledge representation learning is oriented to model the entities and relationships in knowledge bases. In this paper, we first introduce the idea of knowledge representation learning into network representation learning, namely, we propose a new approach to model the vertex triplet relationships based on DeepWalk without TransE. Consequently, we propose an optimized network representation learning algorithm using multi-relational data, MRNR, which introduces the multi-relational data between vertices into the procedures of network representation learning. Importantly, we adopted a kind of higher order transformation strategy to optimize the learnt network representation vectors. The purpose of MRNR is that multi-relational data (triplets) can effectively guide and constrain the procedures of network representation learning. The experimental results demonstrate that the proposed MRNR can learn the discriminative network representations, which show better performance on network classification, visualization, and case study tasks compared to the proposed baseline algorithms in this paper.

APA, Harvard, Vancouver, ISO, and other styles

13

Millán-Martínez, Pere, and Pedro Valero-Mora. "Automating statistical diagrammatic representations with data characterization." Information Visualization 17, no. 4 (July 21, 2017): 316–34. http://dx.doi.org/10.1177/1473871617715326.

Full text

Abstract:

The search for an efficient method to enhance data cognition is especially important when managing data from multidimensional databases. Open data policies have dramatically increased not only the volume of data available to the public, but also the need to automate the translation of data into efficient graphical representations. Graphic automation involves producing an algorithm that necessarily contains inputs derived from the type of data. A set of rules are then applied to combine the input variables and produce a graphical representation. Automated systems, however, fail to provide an efficient graphical representation because they only consider either a one-dimensional characterization of variables, which leads to an overwhelmingly large number of available solutions, a compositional algebra that leads to a single solution, or requires the user to predetermine the graphical representation. Therefore, we propose a multidimensional characterization of statistical variables that when complemented with a catalog of graphical representations that match any single combination, presents the user with a more specific set of suitable graphical representations to choose from. Cognitive studies can then determine the most efficient perceptual procedures to further shorten the path to the most efficient graphical representations. The examples used herein are limited to graphical representations with three variables given that the number of combinations increases drastically as the number of selected variables increases.

APA, Harvard, Vancouver, ISO, and other styles

14

Gutsche, Oliver, and Igor Mandrichenko. "Striped Data Analysis Framework." EPJ Web of Conferences 245 (2020): 06042. http://dx.doi.org/10.1051/epjconf/202024506042.

Full text

Abstract:

A columnar data representation is known to be an efficient way for data storage, specifically in cases when the analysis is often done based only on a small fragment of the available data structures. A data representation like Apache Parquet is a step forward from a columnar representation, which splits data horizontally to allow for easy parallelization of data analysis. Based on the general idea of columnar data storage, working on the [LDRD Project], we have developed a striped data representation, which, we believe, is better suited to the needs of High Energy Physics data analysis. A traditional columnar approach allows for efficient data analysis of complex structures. While keeping all the benefits of columnar data representations, the striped mechanism goes further by enabling easy parallelization of computations without requiring special hardware. We will present an implementation and some performance characteristics of such a data representation mechanism using a distributed no-SQL database or a local file system, unified under the same API and data representation model. The representation is efficient and at the same time simple so that it allows for a common data model and APIs for wide range of underlying storage mechanisms such as distributed no-SQL databases and local file systems. Striped storage adopts Numpy arrays as its basic data representation format, which makes it easy and efficient to use in Python applications. The Striped Data Server is a web service, which allows to hide the server implementation details from the end user, easily exposes data to WAN users, and allows to utilize well known and developed data caching solutions to further increase data access efficiency. We are considering the Striped Data Server as the core of an enterprise scale data analysis platform for High Energy Physics and similar areas of data processing. We have been testing this architecture with a 2TB dataset from a CMS dark matter search and plan to expand it to multiple 100 TB or even PB scale. We will present the striped format, Striped Data Server architecture and performance test results.

APA, Harvard, Vancouver, ISO, and other styles

15

Dokken, T., V. Skytt, and O. Barrowclough. "LOCALLY REFINED SPLINES REPRESENTATION FOR GEOSPATIAL BIG DATA." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL-3/W3 (August 20, 2015): 565–70. http://dx.doi.org/10.5194/isprsarchives-xl-3-w3-565-2015.

Full text

Abstract:

When viewed from distance, large parts of the topography of landmasses and the bathymetry of the sea and ocean floor can be regarded as a smooth background with local features. Consequently a digital elevation model combining a compact smooth representation of the background with locally added features has the potential of providing a compact and accurate representation for topography and bathymetry. The recent introduction of Locally Refined B-Splines (LR B-splines) allows the granularity of spline representations to be locally adapted to the complexity of the smooth shape approximated. This allows few degrees of freedom to be used in areas with little variation, while adding extra degrees of freedom in areas in need of more modelling flexibility. In the EU fp7 Integrating Project IQmulus we exploit LR B-splines for approximating large point clouds representing bathymetry of the smooth sea and ocean floor. A drastic reduction is demonstrated in the bulk of the data representation compared to the size of input point clouds. The representation is very well suited for exploiting the power of GPUs for visualization as the spline format is transferred to the GPU and the triangulation needed for the visualization is generated on the GPU according to the viewing parameters. The LR B-splines are interoperable with other elevation model representations such as LIDAR data, raster representations and triangulated irregular networks as these can be used as input to the LR B-spline approximation algorithms. Output to these formats can be generated from the LR B-spline applications according to the resolution criteria required. The spline models are well suited for change detection as new sensor data can efficiently be compared to the compact LR B-spline representation.

APA, Harvard, Vancouver, ISO, and other styles

16

Hawkins, Peter, Alex Aiken, Kathleen Fisher, Martin Rinard, and Mooly Sagiv. "Concurrent data representation synthesis." ACM SIGPLAN Notices 47, no. 6 (August 6, 2012): 417–28. http://dx.doi.org/10.1145/2345156.2254114.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Kim, Sunghwan, and Jihong Kim. "Low-power data representation." Electronics Letters 36, no. 11 (2000): 958. http://dx.doi.org/10.1049/el:20000722.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

G., Girish, and Ashok Deorari. "Numerical Representation of Data." Journal of Neonatology 19, no. 2 (June 2005): 160–63. http://dx.doi.org/10.1177/0973217920050211.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Jean, Neal, Sherrie Wang, Anshul Samar, George Azzari, David Lobell, and Stefano Ermon. "Tile2Vec: Unsupervised Representation Learning for Spatially Distributed Data." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 3967–74. http://dx.doi.org/10.1609/aaai.v33i01.33013967.

Full text

Abstract:

Geospatial analysis lacks methods like the word vector representations and pre-trained networks that significantly boost performance across a wide range of natural language and computer vision tasks. To fill this gap, we introduce Tile2Vec, an unsupervised representation learning algorithm that extends the distributional hypothesis from natural language — words appearing in similar contexts tend to have similar meanings — to spatially distributed data. We demonstrate empirically that Tile2Vec learns semantically meaningful representations for both image and non-image datasets. Our learned representations significantly improve performance in downstream classification tasks and, similarly to word vectors, allow visual analogies to be obtained via simple arithmetic in the latent space.

APA, Harvard, Vancouver, ISO, and other styles

20

Susanti, Susanti, Zainal Abidin, and Rina Mauliza. "ANALISIS KEMAMPUAN REPRESENTASI MATEMATIS SISWA MELALUI PENERAPAN STRATEGI SCAFFOLDING." Jurnal Ilmiah Pendidikan Matematika Al Qalasadi 5, no. 1 (July 9, 2021): 99–116. http://dx.doi.org/10.32505/qalasadi.v5i1.2912.

Full text

Abstract:

This descriptive qualitative research aims to describe the mathematical representation abilities of students through the application of the scaffolding strategy. The subjects of this study were 2 students with low representation abilities and 2 students with moderate representation abilities in class VIII-4 of SMP Negeri 6 Banda Aceh. The data was collected by means of a mathematical representation ability test sheet, interviews, and a recording device. Then data analysis by reducing data, presenting data, triangulating time, and drawing conclusions. The results showed that subjects with low representation skills tended to perform visual representations, but after scaffolding they were able to use visual representations independently and verbal representations by checking several times. Meanwhile, subjects with moderate representation ability tend to perform visual and verbal representations with multiple checks and symbolic representations with several interventions, after scaffolding they are able to use visual and verbal representations independently, even though symbolic representations still require several interventions. This shows that the students' representation ability gets better after being given a scaffolding strategy.

APA, Harvard, Vancouver, ISO, and other styles

21

olde Scheper, Tjeerd V. "Criticality Analysis: Bio-Inspired Nonlinear Data Representation." Entropy 25, no. 12 (December 14, 2023): 1660. http://dx.doi.org/10.3390/e25121660.

Full text

Abstract:

The representation of arbitrary data in a biological system is one of the most elusive elements of biological information processing. The often logarithmic nature of information in amplitude and frequency presented to biosystems prevents simple encapsulation of the information contained in the input. Criticality Analysis (CA) is a bio-inspired method of information representation within a controlled Self-Organised Critical system that allows scale-free representation. This is based on the concept of a reservoir of dynamic behaviour in which self-similar data will create dynamic nonlinear representations. This unique projection of data preserves the similarity of data within a multidimensional neighbourhood. The input can be reduced dimensionally to a projection output that retains the features of the overall data, yet has a much simpler dynamic response. The method depends only on the Rate Control of Chaos applied to the underlying controlled models, which allows the encoding of arbitrary data and promises optimal encoding of data given biologically relevant networks of oscillators. The CA method allows for a biologically relevant encoding mechanism of arbitrary input to biosystems, creating a suitable model for information processing in varying complexity of organisms and scale-free data representation for machine learning.

APA, Harvard, Vancouver, ISO, and other styles

22

Ruliani, Iva Desi, Nizaruddin Nizaruddin, and Yanuar Hery Murtianto. "Profile Analysis of Mathematical Problem Solving Abilities with Krulik & Rudnick Stages Judging from Medium Visual Representation." JIPM (Jurnal Ilmiah Pendidikan Matematika) 7, no. 1 (September 7, 2018): 22. http://dx.doi.org/10.25273/jipm.v7i1.2123.

Full text

Abstract:

The ability to solve mathematical problems is very important in learning math and everyday life. According to Krulik & Rudnick there are 5 stages of problem solving that is Read, Explore, Select A Strategy, Solve And Look Back. Mathematical problems require multiple representational skills to communicate problems, one of which is visual representation. Trigonometry is one of the materials that uses visual representation. This research is a qualitative descriptive research that aims to describe the ability of problem solving mathematics with Krulik & Rudnick stages in terms of visual representation. The study was conducted in MAN 2 Brebes. Determination of Subjects in this study using Purposive Sampling. Research instruments used to obtain the required data are visual representation and problem-solving tests, and interview guidelines. The data obtained were analyzed based on the Krulik & Rudnick problem solving indicator. Subjects in this study were subjects with moderate visual representation. Based on the results, problem solving ability of the subject is not fully fulfilled. Subjects with visual representations are able to do problem solving well that is solving the problem through a concept that is understood without visualization of the image. Subjects with visual representations are having a schematic visual representation type.

APA, Harvard, Vancouver, ISO, and other styles

23

Nguyễn, Tuấn, Nguyen Hai Hao, Dang Le Dinh Trang, Nguyen Van Tuan, and Cao Van Loi. "Robust anomaly detection methods for contamination network data." Journal of Military Science and Technology, no. 79 (May 19, 2022): 41–51. http://dx.doi.org/10.54939/1859-1043.j.mst.79.2022.41-51.

Full text

Abstract:

Recently, latent representation models, such as Shrink Autoencoder (SAE), have been demonstrated as robust feature representations for one-class learning-based network anomaly detection. In these studies, benchmark network datasets that are processed in laboratory environments to make them completely clean are often employed for constructing and evaluating such models. In real-world scenarios, however, we can not guarantee 100% to collect pure normal data for constructing latent representation models. Therefore, this work aims to investigate the characteristics of the latent representation of SAE in learning normal data under some contamination scenarios. This attempts to find out wherever the latent feature space of SAE is robust to contamination or not, and which contamination scenarios it prefers. We design a set of experiments using normal data contaminated with different anomaly types and different proportions of anomalies for the investigation. Other latent representation methods such as Denoising Autoencoder (DAE) and Principal component analysis (PCA) are also used for comparison with the performance of SAE. The experimental results on four CTU13 scenarios show that the latent representation of SAE often out-performs and are less sensitive to contamination than the others.

APA, Harvard, Vancouver, ISO, and other styles

24

Du, Xin, Yulong Pei, Wouter Duivesteijn, and Mykola Pechenizkiy. "Fairness in Network Representation by Latent Structural Heterogeneity in Observational Data." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 3809–16. http://dx.doi.org/10.1609/aaai.v34i04.5792.

Full text

Abstract:

While recent advances in machine learning put many focuses on fairness of algorithmic decision making, topics about fairness of representation, especially fairness of network representation, are still underexplored. Network representation learning learns a function mapping nodes to low-dimensional vectors. Structural properties, e.g. communities and roles, are preserved in the latent embedding space. In this paper, we argue that latent structural heterogeneity in the observational data could bias the classical network representation model. The unknown heterogeneous distribution across subgroups raises new challenges for fairness in machine learning. Pre-defined groups with sensitive attributes cannot properly tackle the potential unfairness of network representation. We propose a method which can automatically discover subgroups which are unfairly treated by the network representation model. The fairness measure we propose can evaluate complex targets with multi-degree interactions. We conduct randomly controlled experiments on synthetic datasets and verify our methods on real-world datasets. Both quantitative and quantitative results show that our method is effective to recover the fairness of network representations. Our research draws insight on how structural heterogeneity across subgroups restricted by attributes would affect the fairness of network representation learning.

APA, Harvard, Vancouver, ISO, and other styles

25

Schmidt, Tim, and Rong Zhou. "Representing Pattern Databases with Succinct Data Structures." Proceedings of the International Symposium on Combinatorial Search 2, no. 1 (August 19, 2021): 142–49. http://dx.doi.org/10.1609/socs.v2i1.18195.

Full text

Abstract:

In this paper we describe novel representations for precomputed heuristics based on Level-Ordered Edge Sequence (LOES) encodings. We introduce compressed LOES, an extension to LOES that enables more aggressive compression of the state-set representation. We evaluate the novel repre- sentations against the respective perfect-hash and binary decision diagram (BDD) representations of pattern databases in a variety of STRIPS domains.

APA, Harvard, Vancouver, ISO, and other styles

26

Chen, Muyi, Daling Wang, Shi Feng, and Yifei Zhang. "Denoising in Representation Space via Data-Dependent Regularization for Better Representation." Mathematics 11, no. 10 (May 16, 2023): 2327. http://dx.doi.org/10.3390/math11102327.

Full text

Abstract:

Despite the success of deep learning models, it remains challenging for the over-parameterized model to learn good representation under small-sample-size settings. In this paper, motivated by previous work on out-of-distribution (OoD) generalization, we study the representation learning problem from an OoD perspective to identify the fundamental factors affecting representation quality. We formulate a notion of “out-of-feature subspace (OoFS) noise” for the first time, and we link the OoFS noise in the feature extractor to the OoD performance of the model by proving two theorems that demonstrate that reducing OoFS noise in the feature extractor is beneficial in achieving better representation. Moreover, we identify two causes of OoFS noise and prove that the OoFS noise induced by random initialization can be filtered out via L2 regularization. Finally, we propose a novel data-dependent regularizer that acts on the weights of the fully connected layer to reduce noise in the representations, thus implicitly forcing the feature extractor to focus on informative features and to rely less on noise via back-propagation. Experiments on synthetic datasets show that our method can learn hard-to-learn features; can filter out noise effectively; and outperforms GD, AdaGrad, and KFAC. Furthermore, experiments on the benchmark datasets show that our method achieves the best performance for three tasks among four.

APA, Harvard, Vancouver, ISO, and other styles

27

Hochstuhl, Sylvia, Niklas Pfeffer, Antje Thiele, Horst Hammer, and Stefan Hinz. "Your Input Matters—Comparing Real-Valued PolSAR Data Representations for CNN-Based Segmentation." Remote Sensing 15, no. 24 (December 15, 2023): 5738. http://dx.doi.org/10.3390/rs15245738.

Full text

Abstract:

Inspired by the success of Convolutional Neural Network (CNN)-based deep learning methods for optical image segmentation, there is a growing interest in applying these methods to Polarimetric Synthetic Aperture Radar (PolSAR) data. However, effectively utilizing well-established real-valued CNNs for PolSAR image segmentation requires converting complex-valued data into real-valued representations. This paper presents a systematic comparison of 14 different real-valued representations used as CNN input in the literature. These representations encompass various approaches, including the use of coherency matrix elements, hand-crafted feature vectors, polarimetric features based on target decomposition, and combinations of these methods. The goal is to assess the impact of the choice of PolSAR data representation on segmentation performance and identify the most suitable representation. Four test configurations are employed to achieve this, involving different CNN architectures (U-Net with ResNet-18 or EfficientNet backbone) and PolSAR data acquired in different frequency bands (S- and L-band). The results emphasize the importance of selecting an appropriate real-valued representation for CNN-based PolSAR image segmentation. This study’s findings reveal that combining multiple polarimetric features can potentially enhance segmentation performance but does not consistently improve the results. Therefore, when employing this approach, careful feature selection becomes crucial. In contrast, using coherency matrix elements with amplitude and phase representation consistently achieves high segmentation performance across different test configurations. This representation emerges as one of the most suitable approaches for CNN-based PolSAR image segmentation. Notably, it outperforms the commonly used alternative approach of splitting the coherency matrix elements into real and imaginary parts.

APA, Harvard, Vancouver, ISO, and other styles

28

Yang, Qing, Jun Chen, and Najla Al-Nabhan. "Data representation using robust nonnegative matrix factorization for edge computing." Mathematical Biosciences and Engineering 19, no. 2 (2021): 2147–78. http://dx.doi.org/10.3934/mbe.2022100.

Full text

Abstract:

<abstract> <p>As a popular data representation technique, Nonnegative matrix factorization (NMF) has been widely applied in edge computing, information retrieval and pattern recognition. Although it can learn parts-based data representations, existing NMF-based algorithms fail to integrate local and global structures of data to steer matrix factorization. Meanwhile, semi-supervised ones ignore the important role of instances from different classes in learning the representation. To solve such an issue, we propose a novel semi-supervised NMF approach via joint graph regularization and constraint propagation for edge computing, called robust constrained nonnegative matrix factorization (RCNMF), which learns robust discriminative representations by leveraging the power of both L2, 1-norm NMF and constraint propagation. Specifically, RCNMF explicitly exploits global and local structures of data to make latent representations of instances involved by the same class closer and those of instances involved by different classes farther. Furthermore, RCNMF introduces the L2, 1-norm cost function for addressing the problems of noise and outliers. Moreover, L2, 1-norm constraints on the factorial matrix are used to ensure the new representation sparse in rows. Finally, we exploit an optimization algorithm to solve the proposed framework. The convergence of such an optimization algorithm has been proven theoretically and empirically. Empirical experiments show that the proposed RCNMF is superior to other state-of-the-art algorithms.</p> </abstract>

APA, Harvard, Vancouver, ISO, and other styles

29

Hong, Wanrong, Sili Zhu, and Jun Li. "Data-Driven Field Representations and Measuring Processes." Foundations 4, no. 1 (January 30, 2024): 61–79. http://dx.doi.org/10.3390/foundations4010006.

Full text

Abstract:

Natural mathematical objects for representing spatially distributed physical attributes are 3D field functions, which are prevalent in applied sciences and engineering, including areas such as fluid dynamics and computational geometry. The representations of these objects are task-oriented, which are achieved using various techniques that are suitable for specific areas. A recent breakthrough involves using flexible parameterized representations, particularly through neural networks, to model a range of field functions. This technique aims to uncover fields for computational vision tasks, such as representing light-scattering fields. Its effectiveness has led to rapid advancements, enabling the modeling of time dependence in various applications. This survey provides an informative taxonomy of the recent literature in the field of learnable field representation, as well as a comprehensive summary in the application field of visual computing. Open problems in field representation and learning are also discussed, which help shed light on future research.

APA, Harvard, Vancouver, ISO, and other styles

30

Bona, Jonathan P., Fred W. Prior, Meredith N. Zozus, and Mathias Brochhausen. "Enhancing Clinical Data and Clinical Research Data with Biomedical Ontologies - Insights from the Knowledge Representation Perspective." Yearbook of Medical Informatics 28, no. 01 (August 2019): 140–51. http://dx.doi.org/10.1055/s-0039-1677912.

Full text

Abstract:

Objectives: There exists a communication gap between the biomedical informatics community on one side and the computer science/artificial intelligence community on the other side regarding the meaning of the terms “semantic integration" and “knowledge representation“. This gap leads to approaches that attempt to provide one-to-one mappings between data elements and biomedical ontologies. Our aim is to clarify the representational differences between traditional data management and semantic-web-based data management by providing use cases of clinical data and clinical research data re-representation. We discuss how and why one-to-one mappings limit the advantages of using Semantic Web Technologies (SWTs). Methods: We employ commonly used SWTs, such as Resource Description Framework (RDF) and Ontology Web Language (OWL). We reuse pre-existing ontologies and ensure shared ontological commitment by selecting ontologies from a framework that fosters community-driven collaborative ontology development for biomedicine following the same set of principles. Results: We demonstrate the results of providing SWT-compliant re-representation of data elements from two independent projects managing clinical data and clinical research data. Our results show how one-to-one mappings would hinder the exploitation of the advantages provided by using SWT. Conclusions: We conclude that SWT-compliant re-representation is an indispensable step, if using the full potential of SWT is the goal. Rather than providing one-to-one mappings, developers should provide documentation that links data elements to graph structures to specify the re-representation.

APA, Harvard, Vancouver, ISO, and other styles

31

Popal, Haroon, Yin Wang, and Ingrid R. Olson. "A Guide to Representational Similarity Analysis for Social Neuroscience." Social Cognitive and Affective Neuroscience 14, no. 11 (November 1, 2019): 1243–53. http://dx.doi.org/10.1093/scan/nsz099.

Full text

Abstract:

Abstract Representational similarity analysis (RSA) is a computational technique that uses pairwise comparisons of stimuli to reveal their representation in higher-order space. In the context of neuroimaging, mass-univariate analyses and other multivariate analyses can provide information on what and where information is represented but have limitations in their ability to address how information is represented. Social neuroscience is a field that can particularly benefit from incorporating RSA techniques to explore hypotheses regarding the representation of multidimensional data, how representations can predict behavior, how representations differ between groups and how multimodal data can be compared to inform theories. The goal of this paper is to provide a practical as well as theoretical guide to implementing RSA in social neuroscience studies.

APA, Harvard, Vancouver, ISO, and other styles

32

kumar, Vinesh, Dr Amit Asthana, Sunil Kumar, and Dr Jayant Shekhar. "Data Representation in Big data via Succinct Data Structures." International Journal of Engineering Science and Technology 10, no. 1 (January 31, 2018): 21–28. http://dx.doi.org/10.21817/ijest/2018/v10i1/181001013.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Ding, Huijie, and Arthur K. L. Lin. "Feature Extraction Based on Non-Subsampled Shearlet Transform (NSST) with Application to SAR Image Data." Mathematical Problems in Engineering 2020 (November 19, 2020): 1–6. http://dx.doi.org/10.1155/2020/8885887.

Full text

Abstract:

Considering the defaults in synthetic aperture radar (SAR) image feature extraction, an SAR target recognition method based on non-subsampled Shearlet transform (NSST) was proposed with application to target recognition. NSST was used to decompose an SAR image into multilevel representations. These representations were translation-invariant, and they could well reflect the dominant and detailed properties of the target. During the machine learning classification stage, the joint sparse representation was employed to jointly represent the multilevel representations. The joint sparse representation could represent individual components independently while considering the inner correlations between different components. Therefore, the precision of joint representation could be enhanced. Finally, the target label of the test sample was determined according to the overall reconstruction error. Experiments were conducted on the MSTAR dataset to examine the proposed method, and the results confirmed its validity and robustness under the standard operating condition, configuration variance, depression angle variance, and noise corruption.

APA, Harvard, Vancouver, ISO, and other styles

34

Zhang, Shichao, Jiaye Li, Wenzhen Zhang, and Yongsong Qin. "Hyper-class representation of data." Neurocomputing 503 (September 2022): 200–218. http://dx.doi.org/10.1016/j.neucom.2022.06.082.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Badaro, Gilbert, and Paolo Papotti. "Transformers for tabular data representation." Proceedings of the VLDB Endowment 15, no. 12 (August 2022): 3746–49. http://dx.doi.org/10.14778/3554821.3554890.

Full text

Abstract:

In the last few years, the natural language processing community witnessed advances in neural representations of free texts with transformer-based language models (LMs). Given the importance of knowledge available in relational tables, recent research efforts extend LMs by developing neural representations for tabular data. In this tutorial, we present these proposals with two main goals. First, we introduce to a database audience the potentials and the limitations of current models. Second, we demonstrate the large variety of data applications that benefit from the transformer architecture. The tutorial aims at encouraging database researchers to engage and contribute to this new direction, and at empowering practitioners with a new set of tools for applications involving text and tabular data.

APA, Harvard, Vancouver, ISO, and other styles

36

S.Fadel, Ahmed, Mohamed Belal, and Mostafa-Sami M. Mostafa. "Protein Data Representation: A Survey." International Journal of Computer Applications 56, no. 11 (October 20, 2012): 22–27. http://dx.doi.org/10.5120/8936-3075.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Piech, M. Ann, and Kenneth R. Piech. "Symbolic representation of hyperspectral data." Applied Optics 26, no. 18 (September 15, 1987): 4018. http://dx.doi.org/10.1364/ao.26.004018.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Sholomov, L. A. "Binary representation of underdetermined data." Doklady Mathematics 87, no. 1 (February 2013): 116–19. http://dx.doi.org/10.1134/s1064562413010201.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Kozarzewski, Bohdan. "Numerical Representation of Symbolic Data." Computational Methods in Science and Technology 21, no. 04 (2015): 241–49. http://dx.doi.org/10.12921/cmst.2015.21.04.008.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Ermann, Michael, and John Samuel Victor. "Graphical representation of acoustic data." Journal of the Acoustical Society of America 124, no. 4 (October 2008): 2588. http://dx.doi.org/10.1121/1.4783211.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Guangqiang, Xie, and Li Yang. "Extension Data Mining Knowledge Representation." Physics Procedia 24 (2012): 240–46. http://dx.doi.org/10.1016/j.phpro.2012.02.036.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Polimeni, Jonathan, and Eric Schwartz. "Neural representation of sensory data." Behavioral and Brain Sciences 25, no. 2 (April 2002): 207–8. http://dx.doi.org/10.1017/s0140525x02470045.

Full text

Abstract:

In the target article Pylyshyn revives the spectre of the “little green man,” arguing for a largely symbolic representation of visual imagery. To clarify this problem, we provide precise definitions of the key term “picture,” present some examples of our definition, and outline an information-theoretic analysis suggesting that the problem of addressing data in the brain requires a partially analogue and partially symbolic solution. This is made concrete in the ventral stream of object recognition, from V1 to IT cortex.

APA, Harvard, Vancouver, ISO, and other styles

43

Guo, Jingzhi, and Chengzheng Sun. "Context representation of product data." ACM SIGecom Exchanges 4, no. 1 (March 2003): 20–28. http://dx.doi.org/10.1145/844357.844364.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Greet, R., and M. M. Wind. "Polar representation of ellipsometric data." Applied Optics 25, no. 10 (May 15, 1986): 1627. http://dx.doi.org/10.1364/ao.25.001627.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Ferrari, A., F. X. Schmider, A. Alengrin, and B. Gelly. "Parametric representation of helioseismic data." Astronomy and Astrophysics Supplement Series 138, no. 1 (July 1999): 177–85. http://dx.doi.org/10.1051/aas:1999493.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Yanhui Xiao, Zhenfeng Zhu, Yao Zhao, Yunchao Wei, Shikui Wei, and Xuelong Li. "Topographic NMF for Data Representation." IEEE Transactions on Cybernetics 44, no. 10 (October 2014): 1762–71. http://dx.doi.org/10.1109/tcyb.2013.2294215.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

MORRISON, PHILIP S. "Symbolic Representation of Tabular Data." New Zealand Journal of Geography 79, no. 1 (May 15, 2008): 11–18. http://dx.doi.org/10.1111/j.0028-8292.1985.tb00199.x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

de Valk, J. P. J., W. J. M. Epping, and A. Heringa. "Colour representation of biomedical data." Medical and Biological Engineering and Computing 23, no. 4 (July 1985): 343–51. http://dx.doi.org/10.1007/bf02441588.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Sloot, Peter M. A., and Carl G. Figdor. "Ternary representation of trivariate data." Cytometry 10, no. 1 (January 1989): 77–80. http://dx.doi.org/10.1002/cyto.990100113.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Ellwein, Carsten, Rebekka Neumann, and Alexander Verl. "Software-defined Manufacturing: Data Representation." Procedia CIRP 118 (2023): 360–65. http://dx.doi.org/10.1016/j.procir.2023.06.062.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Data representation'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles