Journal articles: 'Latent space analysis'

1

Liu, Yang, Eunice Jun, Qisheng Li, and Jeffrey Heer. "Latent Space Cartography: Visual Analysis of Vector Space Embeddings." Computer Graphics Forum 38, no. 3 (June 2019): 67–78. http://dx.doi.org/10.1111/cgf.13672.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Valtazanos, Aris, D. K. Arvind, and Subramanian Ramamoorthy. "Latent space segmentation for mobile gait analysis." ACM Transactions on Embedded Computing Systems 12, no. 4 (June 2013): 1–22. http://dx.doi.org/10.1145/2485984.2485989.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Hoff, Peter D., Adrian E. Raftery, and Mark S. Handcock. "Latent Space Approaches to Social Network Analysis." Journal of the American Statistical Association 97, no. 460 (December 2002): 1090–98. http://dx.doi.org/10.1198/016214502388618906.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Sarkar, Purnamrita, and Andrew W. Moore. "Dynamic social network analysis using latent space models." ACM SIGKDD Explorations Newsletter 7, no. 2 (December 2005): 31–40. http://dx.doi.org/10.1145/1117454.1117459.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Linardi, Fernando, Cees Diks, Marco van der Leij, and Iuri Lazier. "Dynamic interbank network analysis using latent space models." Journal of Economic Dynamics and Control 112 (March 2020): 103792. http://dx.doi.org/10.1016/j.jedc.2019.103792.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Ng, Ka Chung, Mike K. P. So, and Kar Yan Tam. "A Latent Space Modeling Approach to Interfirm Relationship Analysis." ACM Transactions on Management Information Systems 12, no. 2 (June 2021): 1–44. http://dx.doi.org/10.1145/3424240.

Full text

Abstract:

Interfirm relationships are crucial to our understanding of firms’ collective and interactive behavior. Many information systems-related phenomena, including the diffusion of innovations, standard alliances, technology collaboration, and outsourcing, involve a multitude of relationships between firms. This study proposes a latent space approach to model temporal change in a dual-view interfirm network. We assume that interfirm relationships depend on an underlying latent space; firms that are close to each other in the latent space are more likely to develop a relationship. We construct the latent space by embedding two dynamic networks of firms in an integrated manner, resulting in a more comprehensive view of an interfirm relationship. We validate our approach by introducing three business measures derived from the latent space model to study alliance formation and stock comovement. We illustrate how the trajectories of firms provide insights into alliance activities. We also show that our proposed measures have strong predictive power on stock comovement. We believe the proposed approach enriches the methodology toolbox of IS researchers in studying interfirm relationships.

APA, Harvard, Vancouver, ISO, and other styles

7

Kuang, Zhanghui, and Kwan-Yee K. Wong. "Relatively-Paired Space Analysis: Learning a Latent Common Space From Relatively-Paired Observations." International Journal of Computer Vision 113, no. 3 (November 12, 2014): 176–92. http://dx.doi.org/10.1007/s11263-014-0783-8.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

CHEN, YIXIN, DONG HUA, and FANG LIU. "GENERALIZED LATENT CLASS ANALYSIS BASED ON MODEL DOMINANCE THEORY." International Journal on Artificial Intelligence Tools 18, no. 05 (October 2009): 739–55. http://dx.doi.org/10.1142/s021821300900038x.

Full text

Abstract:

Latent class analysis is a popular statistical learning approach. A major challenge for learning generalized latent class is the complexity in searching the huge space of models and parameters. The computational cost is higher when the model topology is more flexible. In this paper, we propose the notion of dominance which can lead to strong pruning of the search space and significant reduction of learning complexity, and apply this notion to the Generalized Latent Class (GLC) models, a class of Bayesian networks for clustering categorical data. GLC models can address the local dependence problem in latent class analysis by assuming a very general graph structure. However, The flexible topology of GLC leads to large increase of the learning complexity. We first propose the concept of dominance and related theoretical results which is general for all Bayesian networks. Based on dominance, we propose an efficient learning algorithm for GLC. A core technique to prune dominated models is regularization, which can eliminate dominated models, leading to significant pruning of the search space. Significant improvements on the model.

APA, Harvard, Vancouver, ISO, and other styles

9

Aswani Kumar, Ch, M. Radvansky, and J. Annapurna. "Analysis of a Vector Space Model, Latent Semantic Indexing and Formal Concept Analysis for Information Retrieval." Cybernetics and Information Technologies 12, no. 1 (March 1, 2012): 34–48. http://dx.doi.org/10.2478/cait-2012-0003.

Full text

Abstract:

Abstract Latent Semantic Indexing (LSI), a variant of classical Vector Space Model (VSM), is an Information Retrieval (IR) model that attempts to capture the latent semantic relationship between the data items. Mathematical lattices, under the framework of Formal Concept Analysis (FCA), represent conceptual hierarchies in data and retrieve the information. However, both LSI and FCA use the data represented in the form of matrices. The objective of this paper is to systematically analyze VSM, LSI and FCA for the task of IR using standard and real life datasets.

APA, Harvard, Vancouver, ISO, and other styles

10

Chu, Amanda M. Y., Thomas W. C. Chan, Mike K. P. So, and Wing-Keung Wong. "Dynamic Network Analysis of COVID-19 with a Latent Pandemic Space Model." International Journal of Environmental Research and Public Health 18, no. 6 (March 19, 2021): 3195. http://dx.doi.org/10.3390/ijerph18063195.

Full text

Abstract:

In this paper, we propose a latent pandemic space modeling approach for analyzing coronavirus disease 2019 (COVID-19) pandemic data. We developed a pandemic space concept that locates different regions so that their connections can be quantified according to the distances between them. A main feature of the pandemic space is to allow visualization of the pandemic status over time through the connectedness between regions. We applied the latent pandemic space model to dynamic pandemic networks constructed using data of confirmed cases of COVID-19 in 164 countries. We observed the ways in which pandemic risk evolves by tracing changes in the locations of countries within the pandemic space. Empirical results gained through this pandemic space analysis can be used to quantify the effectiveness of lockdowns, travel restrictions, and other measures in regard to reducing transmission risk across countries.

APA, Harvard, Vancouver, ISO, and other styles

11

Sharma, Abhishek, Murad Al Haj, Jonghyun Choi, Larry S. Davis, and David W. Jacobs. "Robust pose invariant face recognition using coupled latent space discriminant analysis." Computer Vision and Image Understanding 116, no. 11 (November 2012): 1095–110. http://dx.doi.org/10.1016/j.cviu.2012.08.001.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Linhardt, Timothy, and Ananya Sen Gupta. "Empirical analysis of latent space encodings for submerged small target acoustic backscattering data." Journal of the Acoustical Society of America 151, no. 4 (April 2022): A102. http://dx.doi.org/10.1121/10.0010792.

Full text

Abstract:

With future sights on specialized classification methods, we work to generalize the acoustic backscattering data from sonar measurements of small targets submerged in water by learning a non-invertible mapping (encoding) to a low-dimensional vector space (ℝn). Finding the optimal dimensionality of this latent space is an important task. The encoding is accomplished by utilizing modality agnostic convolutional machine learning methods that have seen success in other signal and image processing domains. We have explored the autoencoder and its variants, the sparse autoencoder, and the variational autoencoder. Autoencoders encode input samples from a high-dimensional manifold to a lower latent vector space and then reverse the lossy mapping back to a high-dimensional manifold similar to the initial domain. The sparse autoencoder induces sparsity in the components of the latent vectors, and the variational autoencoder learns an encoding to n-dimensional gaussian distributions instead of n-dimensional vectors. The TREX13 data are the primary dataset used for training the networks used in experiments. We evaluate the change in models’ accuracies as the latent dimensionality is increased as well as the models’ ability to generalize to unseen data. Additionally, the PONDEX09 and PONDEX10 data are used to evaluate the models’ cross-domain efficacy.

APA, Harvard, Vancouver, ISO, and other styles

13

Lassance, Carlos, Vincent Gripon, and Antonio Ortega. "Representing Deep Neural Networks Latent Space Geometries with Graphs." Algorithms 14, no. 2 (January 27, 2021): 39. http://dx.doi.org/10.3390/a14020039.

Full text

Abstract:

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more detail, we propose to represent geometries by constructing similarity graphs from the intermediate representations obtained when processing a batch of inputs. By constraining these Latent Geometry Graphs (LGGs), we address the three following problems: (i) reproducing the behavior of a teacher architecture is achieved by mimicking its geometry, (ii) designing efficient embeddings for classification is achieved by targeting specific geometries, and (iii) robustness to deviations on inputs is achieved via enforcing smooth variation of geometry between consecutive latent spaces. Using standard vision benchmarks, we demonstrate the ability of the proposed geometry-based methods in solving the considered problems.

APA, Harvard, Vancouver, ISO, and other styles

14

Karami, Mahdi, and Dale Schuurmans. "Deep Probabilistic Canonical Correlation Analysis." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 9 (May 18, 2021): 8055–63. http://dx.doi.org/10.1609/aaai.v35i9.16982.

Full text

Abstract:

We propose a deep generative framework for multi-view learning based on a probabilistic interpretation of canonical correlation analysis (CCA). The model combines a linear multi-view layer in the latent space with deep generative networks as observation models, to decompose the variability in multiple views into a shared latent representation that describes the common underlying sources of variation and a set of viewspecific components. To approximate the posterior distribution of the latent multi-view layer, an efficient variational inference procedure is developed based on the solution of probabilistic CCA. The model is then generalized to an arbitrary number of views. An empirical analysis confirms that the proposed deep multi-view model can discover subtle relationships between multiple views and recover rich representations.

APA, Harvard, Vancouver, ISO, and other styles

15

ASEERVATHAM, SUJEEVAN. "A CONCEPT VECTOR SPACE MODEL FOR SEMANTIC KERNELS." International Journal on Artificial Intelligence Tools 18, no. 02 (April 2009): 239–72. http://dx.doi.org/10.1142/s0218213009000123.

Full text

Abstract:

Kernels are widely used in Natural Language Processing as similarity measures within inner-product based learning methods like the Support Vector Machine. The Vector Space Model (VSM) is extensively used for the spatial representation of the documents. However, it is purely a statistical representation. In this paper, we present a Concept Vector Space Model (CVSM) representation which uses linguistic prior knowledge to capture the meanings of the documents. We also propose a linear kernel and a latent kernel for this space. The linear kernel takes advantage of the linguistic concepts whereas the latent kernel combines statistical and linguistic concepts. Indeed, the latter kernel uses latent concepts extracted by the Latent Semantic Analysis (LSA) in the CVSM. The kernels were evaluated on a text categorization task in the biomedical domain. The Ohsumed corpus, well known for being difficult to categorize, was used. The results have shown that the CVSM improves performance compared to the VSM.

APA, Harvard, Vancouver, ISO, and other styles

16

Fung, Wai-keung, and Yun-hui Liu. "Feature Extraction of Robot Sensor Data Using Factor Analysis for Behavior Learning." Journal of Advanced Computational Intelligence and Intelligent Informatics 8, no. 3 (May 20, 2004): 284–94. http://dx.doi.org/10.20965/jaciii.2004.p0284.

Full text

Abstract:

The paper addresses feature extraction of sensor data for robot behavior learning using factor analysis. Redundancies in sensor types and quantities are common in sensing competence of robots. The redundancies cause the high dimensionality of the perceptual space. It is impractical to incorporate all available sensor information in decision-making and learning of robots due to the huge memory and computational requirements. This paper proposes a new approach to extract important knowledge from sensor data based on the inter-correlation of sensor data using factor analysis and construct logical perceptual space for robot behavior learning. The logical perceptual space is constructed by hypothetical latent factors extracted using factor analysis. Since the latent factors extracted have fewer dimensions than raw sensor data, using the logical perceptual space in behavior learning would significantly simplify the learning process and architecture. Experiments have been conducted to demonstrate the process of logical perceptual space extraction from ultrasonic range data for robot behavior learning.

APA, Harvard, Vancouver, ISO, and other styles

17

Wallet, Bradley C., and Thang N. Ha. "A deep-learning method for latent space analysis of multiple seismic attributes." Interpretation 9, no. 3 (August 1, 2021): T945—T954. http://dx.doi.org/10.1190/int-2020-0194.1.

Full text

Abstract:

Seismic attributes are a well-established method for highlighting subtle features in seismic data to improve interpretability and suitability for quantitative analysis. Seismic attributes are an enabling technology in such areas as thin-bed analysis, geobody extraction, and seismic geomorphology. Seismic attributes are mathematical functions of the data that are designed to exploit geologic and/or geophysical principles to provide meaningful information about underlying processes. Seismic attributes often suffer from an “abundance of riches” because the high dimensionality of seismic attributes may cause great difficulty in accomplishing even simple tasks. Spectral decomposition, for instance, typically produces tens and sometimes hundreds of attributes. However, when it comes to visualization, for instance, we are limited to visualizing three or at most four attributes simultaneously. We have developed a deep-learning-based approach to latent space analysis. This method is superior to other methods in that it focuses upon capturing essential information rather than just focusing upon probability density functions or clusters. Our method provides a quantitative way to assess the fit of the latent space to the original data. We apply our method to a data set from Canterbury Basin, New Zealand. This data set contains a turbidite system, and it has been the subject of several other papers. We examine the goodness of fit of our model by comparing the input data to what can be reproduced, and we provide an interpretation based upon our method.

APA, Harvard, Vancouver, ISO, and other styles

18

YONEKURA, Kazuo. "Quantitative analysis of latent space in airfoil shape generation using variational autoencoders." Transactions of the JSME (in Japanese) 87, no. 903 (2021): 21–00212. http://dx.doi.org/10.1299/transjsme.21-00212.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Deng, P. C., W. H. Gui, and Y. F. Xie. "Latent space transformation based on principal component analysis for adaptive fault detection." IET Control Theory & Applications 4, no. 11 (November 1, 2010): 2527–38. http://dx.doi.org/10.1049/iet-cta.2008.0546.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Grant-Jacob, James A., Michalis N. Zervas, and Ben Mills. "Morphology exploration of pollen using deep learning latent space." IOP SciNotes 3, no. 4 (December 1, 2022): 044602. http://dx.doi.org/10.1088/2633-1357/acadb9.

Full text

Abstract:

Abstract The structure of pollen has evolved depending on its local environment, competition, and ecology. As pollen grains are generally of size 10–100 microns with nanometre-scale substructure, scanning electron microscopy is an important microscopy technique for imaging and analysis. Here, we use style transfer deep learning to allow exploration of latent w-space of scanning electron microscope images of pollen grains and show the potential for using this technique to understand evolutionary pathways and characteristic structural traits of pollen grains.

APA, Harvard, Vancouver, ISO, and other styles

21

Tamosiunas, Andrius, Hans A. Winther, Kazuya Koyama, David J. Bacon, Robert C. Nichol, and Ben Mawdsley. "Investigating cosmological GAN emulators using latent space interpolation." Monthly Notices of the Royal Astronomical Society 506, no. 2 (July 2, 2021): 3049–67. http://dx.doi.org/10.1093/mnras/stab1879.

Full text

Abstract:

ABSTRACT Generative adversarial networks (GANs) have been recently applied as a novel emulation technique for large-scale structure simulations. Recent results show that GANs can be used as a fast and efficient emulator for producing novel weak lensing convergence maps as well as cosmic web data in 2D and 3D. However, like any algorithm, the GAN approach comes with a set of limitations, such as an unstable training procedure, inherent randomness of the produced outputs, and difficulties when training the algorithm on multiple data sets. In this work, we employ a number of techniques commonly used in the machine learning literature to address the mentioned limitations. Specifically, we train a GAN to produce weak lensing convergence maps and dark matter overdensity field data for multiple redshifts, cosmological parameters, and modified gravity models. In addition, we train a GAN using the newest Illustris data to emulate dark matter, gas, and internal energy distribution data simultaneously. Finally, we apply the technique of latent space interpolation as a tool for understanding the feature space of the GAN algorithm. We show that the latent space interpolation procedure allows the generation of outputs with intermediate cosmological parameters that were not included in the training data. Our results indicate a 1–20 per cent difference between the power spectra of the GAN-produced and the test data samples depending on the data set used and whether Gaussian smoothing was applied. Similarly, the Minkowski functional analysis indicates a good agreement between the emulated and the real images for most of the studied data sets.

APA, Harvard, Vancouver, ISO, and other styles

22

Chikkankod, Arjun Vinayak, and Luca Longo. "On the Dimensionality and Utility of Convolutional Autoencoder’s Latent Space Trained with Topology-Preserving Spectral EEG Head-Maps." Machine Learning and Knowledge Extraction 4, no. 4 (November 18, 2022): 1042–64. http://dx.doi.org/10.3390/make4040053.

Full text

Abstract:

Electroencephalography (EEG) signals can be analyzed in the temporal, spatial, or frequency domains. Noise and artifacts during the data acquisition phase contaminate these signals adding difficulties in their analysis. Techniques such as Independent Component Analysis (ICA) require human intervention to remove noise and artifacts. Autoencoders have automatized artifact detection and removal by representing inputs in a lower dimensional latent space. However, little research is devoted to understanding the minimum dimension of such latent space that allows meaningful input reconstruction. Person-specific convolutional autoencoders are designed by manipulating the size of their latent space. A sliding window technique with overlapping is employed to segment varied-sized windows. Five topographic head-maps are formed in the frequency domain for each window. The latent space of autoencoders is assessed using the input reconstruction capacity and classification utility. Findings indicate that the minimal latent space dimension is 25% of the size of the topographic maps for achieving maximum reconstruction capacity and maximizing classification accuracy, which is achieved with a window length of at least 1 s and a shift of 125 ms, using the 128 Hz sampling rate. This research contributes to the body of knowledge with an architectural pipeline for eliminating redundant EEG data while preserving relevant features with deep autoencoders.

APA, Harvard, Vancouver, ISO, and other styles

23

Tong, D. H., X. H. Kong, M. Li, X. Liu, G. L. Huang, and X. P. Wang. "Thermodynamic Analysis of Space Regenerative Orc (Srorc) System for Automotive Waste Heat Recovery." Journal of Physics: Conference Series 2186, no. 1 (February 1, 2022): 012018. http://dx.doi.org/10.1088/1742-6596/2186/1/012018.

Full text

Abstract:

Abstract In this paper, the space regenerative ORC (SRORC) system is proposed. In SRORC system, the superheated working fluid is divided into two parts after it works completely in the expander. The performance of SRORC system is studied, the performance of ORC system and SRORC system under different conditions are compared and analyzed. From the perspective of latent and sensible heat, the mechanism of using space regeneration to improve the performance of SRORC system is explored. The models of ORC system and SRORC system are built by Aspen plus software. R245fa is chosen as the working fluid because of its excellent performance. The simulation results show that compared with the evaporation temperature, the evaporation pressure has greater influence on the performance of SRORC system under B75 condition. Under C25, B50, A75, B75, and B100 conditions, compared with ORC system, the net output power of SRORC system is increased by 30.7%, 30.3%, 34.4%, 33.2% and 34%, the thermal efficiency is increased by 4.3%, 4.36%, 4.97%, 4.79% and 4.89%, the exergy efficiency is increased by 11.13%, 10.28%, 10.36%, 10.69% and 10.02%, the recovery efficiency of engine power is increased by 3.92%, 2.55%, 2.9%, 2.91% and 3.36%, respectively. The heat recovery rate of IHE-ORC system and SRORC system are 13.7kW and 24.8kW under B75 condition. In SRORC system, liquid working fluid can recover sensible and latent heat of superheated working fluid, and the latent heat accounts for most of the heat recovered.

APA, Harvard, Vancouver, ISO, and other styles

24

Aradhya, Abhay M. S., Aditya Joglekar, Sundaram Suresh, and M. Pratama. "Deep Transformation Method for Discriminant Analysis of Multi-Channel Resting State fMRI." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 2556–63. http://dx.doi.org/10.1609/aaai.v33i01.33012556.

Full text

Abstract:

Analysis of resting state - functional Magnetic Resonance Imaging (rs-fMRI) data has been a challenging problem due to a high homogeneity, large intra-class variability, limited samples and difference in acquisition technologies/techniques. These issues are predominant in the case of Attention Deficit Hyperactivity Disorder (ADHD). In this paper, we propose a new Deep Transformation Method (DTM) that extracts the discriminant latent feature space from rsfMRI and projects it in the subsequent layer for classification of rs-fMRI data. The hidden transformation layer in DTM projects the original rs-fMRI data into a new space using the learning policy and extracts the spatio-temporal correlations of the functional activities as a latent feature space. The subsequent convolution and decision layers transform the latent feature space into high-level features and provide accurate classification. The performance of DTM has been evaluated using the ADHD200 rs-fMRI benchmark data with crossvalidation. The results show that the proposed DTM achieves a mean classification accuracy of 70.36% and an improvement of 8.25% on the state of the art methodologies was observed. The improvement is due to concurrent analysis of the spatio-temporal correlations between the different regions of the brain and can be easily extended to study other cognitive disorders using rs-fMRI. Further, brain network analysis has been studied to identify the difference in functional activities and the corresponding regions behind cognitive symptoms in ADHD.

APA, Harvard, Vancouver, ISO, and other styles

25

Bishop, Christopher M., Markus Svensén, and Christopher K. I. Williams. "GTM: The Generative Topographic Mapping." Neural Computation 10, no. 1 (January 1, 1998): 215–34. http://dx.doi.org/10.1162/089976698300017953.

Full text

Abstract:

Latent variable models represent the probability density of data in a space of several dimensions in terms of a smaller number of latent, or hidden, variables. A familiar example is factor analysis, which is based on a linear transformation between the latent space and the data space. In this article, we introduce a form of nonlinear latent variable model called the generative topographic mapping, for which the parameters of the model can be determined using the expectation-maximization algorithm. GTM provides a principled alternative to the widely used self-organizing map (SOM) of Kohonen (1982) and overcomes most of the significant limitations of the SOM. We demonstrate the performance of the GTM algorithm on a toy problem and on simulated data from flow diagnostics for a multiphase oil pipeline.

APA, Harvard, Vancouver, ISO, and other styles

26

Kurby, Christopher A., Katja Wiemer-Hastings, Nagasai Ganduri, Joseph P. Magliano, Keith K. Millis, and Danielle S. McNamara. "Computerizing reading training: Evaluation of a latent semantic analysis space for science text." Behavior Research Methods, Instruments, & Computers 35, no. 2 (May 2003): 244–50. http://dx.doi.org/10.3758/bf03202547.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

Song, Wei, and Soon Cheol Park. "Latent semantic analysis for vector space expansion and fuzzy logic-based genetic clustering." Knowledge and Information Systems 22, no. 3 (February 5, 2009): 347–69. http://dx.doi.org/10.1007/s10115-009-0191-5.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Go, Dongyoung, Minjeong Jeon, Saebyul Lee, Ick Hoon Jin, and Hae-Jeong Park. "Analyzing differences between parent- and self-report measures with a latent space approach." PLOS ONE 17, no. 6 (June 29, 2022): e0269376. http://dx.doi.org/10.1371/journal.pone.0269376.

Full text

Abstract:

We explore potential cross-informant discrepancies between child- and parent-report measures with an example of the Child Behavior Checklist (CBCL) and the Youth Self Report (YSR), parent- and self-report measures on children’s behavioral and emotional problems. We propose a new way of examining the parent- and child-report differences with an interaction map estimated using a Latent Space Item Response Model (LSIRM). The interaction map enables the investigation of the dependency between items, between respondents, and between items and respondents, which is not possible with the conventional approach. The LSIRM captures the differential positions of items and respondents in the latent spaces for CBCL and YSR and identifies the relationships between each respondent and item according to their dependent structures. The results suggest that the analysis of item response in the latent space using the LSIRM is beneficial in uncovering the differential structures embedded in the response data obtained from different perspectives in children and their parents. This study also argues that the differential hidden structures of children and parents’ responses should be taken together to evaluate children’s behavioral problems.

APA, Harvard, Vancouver, ISO, and other styles

29

Kozlowski, Diego, Viktoriya Semeshenko, and Andrea Molinari. "Latent Dirichlet allocation model for world trade analysis." PLOS ONE 16, no. 2 (February 4, 2021): e0245393. http://dx.doi.org/10.1371/journal.pone.0245393.

Full text

Abstract:

International trade is one of the classic areas of study in economics. Its empirical analysis is a complex problem, given the amount of products, countries and years. Nowadays, given the availability of data, the tools used for the analysis can be complemented and enriched with new methodologies and techniques that go beyond the traditional approach. This new possibility opens a research gap, as new, data-driven, ways of understanding international trade, can help our understanding of the underlying phenomena. The present paper shows the application of the Latent Dirichlet allocation model, a well known technique in the area of Natural Language Processing, to search for latent dimensions in the product space of international trade, and their distribution across countries over time. We apply this technique to a dataset of countries’ exports of goods from 1962 to 2016. The results show that this technique can encode the main specialisation patterns of international trade. On the country-level analysis, the findings show the changes in the specialisation patterns of countries over time. As traditional international trade analysis demands expert knowledge on a multiplicity of indicators, the possibility of encoding multiple known phenomena under a unique indicator is a powerful complement for traditional tools, as it allows top-down data-driven studies.

APA, Harvard, Vancouver, ISO, and other styles

30

Sepriano, Alexandre, Sofia Ramiro, Désirée van der Heijde, Floris van Gaalen, Pierre Hoonhout, Anna Molto, Alain Saraux, Roberta Ramonda, Maxime Dougados, and Robert Landewé. "What is axial spondyloarthritis? A latent class and transition analysis in the SPACE and DESIR cohorts." Annals of the Rheumatic Diseases 79, no. 3 (January 24, 2020): 324–31. http://dx.doi.org/10.1136/annrheumdis-2019-216516.

Full text

Abstract:

ObjectivesTo gain expert-judgement-free insight into the Gestalt of axial spondyloarthritis (axSpA), by investigating its ‘latent constructs’ and to test how well these latent constructs fit the Assessment of SpondyloArthritis international Society (ASAS) classification criteria.MethodsTwo independent cohorts of patients with early onset chronic back pain (SPondyloArthritis Caught Early (SPACE)) or inflammatory back pain (IBP) (DEvenir des Spondylarthopathies Indifférenciées Récentes (DESIR)) were analysed. Latent class analysis (LCA) was used to estimate the (unobserved) potential classes underlying axSpA. The best LCA model groups patients into clinically meaningful classes with best fit. Each class was labelled based on most prominent features. Percentage fulfilment of ASAS axSpA, peripheral SpA (pSpA) (ignoring IBP) or both classification criteria was calculated. Five-year data from DESIR were used to perform latent transition analysis (LTA) to examine if patients change classes over time.ResultsSPACE (n=465) yielded four discernible classes: ‘axial’ with highest likelihood of abnormal imaging and HLA-B27 positivity; ‘IBP+peripheral’ with 100% IBP and dominant peripheral symptoms; ‘at risk’ with positive family history and HLA-B27 and ‘no SpA’ with low likelihood for each SpA feature. LCA in DESIR (n=576) yielded similar classes, except for the ‘no-SpA’. The ASAS axSpA criteria captured almost all (SPACE: 98%; DESIR: 93%) ‘axial’ patients, but the ‘IBP+peripheral’ class was only captured well by combining the axSpA and pSpA criteria (SPACE: 78%; DESIR: 89%). Only 4% of ‘no SpA’ patients fulfilled the axSpA criteria in SPACE. LTA suggested that 5-year transitions across classes were unlikely (11%).ConclusionThe Gestalt of axSpA comprises three discernible entities, only appropriately captured by combining the ASAS axSpA and pSpA classification criteria. It is questionable whether some patients with ‘axSpA at risk’ will ever develop axSpA.

APA, Harvard, Vancouver, ISO, and other styles

31

Sun, D., S. Zhao, Z. Zhang, and X. Shi. "AMATCHMETHOD BASED ON LATENT SEMANTIC ANALYSIS FOR EARTHQUAKEHAZARD EMERGENCY PLAN." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-2/W7 (September 12, 2017): 137–41. http://dx.doi.org/10.5194/isprs-archives-xlii-2-w7-137-2017.

Full text

Abstract:

The structure of the emergency plan on earthquake is complex, and it’s difficult for decision maker to make a decision in a short time. To solve the problem, this paper presents a match method based on Latent Semantic Analysis (LSA). After the word segmentation preprocessing of emergency plan, we carry out keywords extraction according to the part-of-speech and the frequency of words. Then through LSA, we map the documents and query information to the semantic space, and calculate the correlation of documents and queries by the relation between vectors. The experiments results indicate that the LSA can improve the accuracy of emergency plan retrieval efficiently.

APA, Harvard, Vancouver, ISO, and other styles

32

Kang, Soo K., and Jaeseok Lee. "A cannabis festival in urban space: visitors' motivation and travel activity." Journal of Hospitality and Tourism Insights 4, no. 2 (March 5, 2021): 142–62. http://dx.doi.org/10.1108/jhti-09-2020-0177.

Full text

Abstract:

PurposeThe present study aimed at classifying cannabis festival attendees based on their motivation and travel activities, profiling the resultant latent groups with demographic and travel characteristics and examining the association between the groups.Design/methodology/approachWith a quantitative-exploratory approach, this study collected 392 out-of-state visitors' responses to a cannabis festival in Denver, Colorado and classified them according to their motivation and activity participation. Using the classification results, the study profiled the festival visitors based on their demographic and travel characteristics. Latent class analysis, analysis of variance (ANOVA) and cross-tabulation were employed.FindingsThe results revealed that festival visitors were categorized into four latent groups by motivation and three latent groups by travel activity participation. Regarding motivation, the cannabis seekers (relatively young, White/Caucasian and residents in liberal states) and multi-purpose seekers (relatively young, Black/African American and residents in conservative states) were strongly motivated by cannabis-related factors. For travel activity participation, moderate participants were more likely to be first-time visitors, whereas active and passive participants were classified as repeat visitors.Originality/valueThe current study filled the research gap in the quantitative exploration of cannabis tourism industry in general and cannabis festival segment specifically. The findings contribute to (1) better understanding of out-of-state visitors' motivation and travel behaviors while attending a cannabis themed festival and (2) serving as a seminal work in the context of cannabis tourism literature since the recreational cannabis legalization in the United States.

APA, Harvard, Vancouver, ISO, and other styles

33

Feeney, Daniel F., François G. Meyer, Nicholas Noone, and Roger M. Enoka. "A latent low-dimensional common input drives a pool of motor neurons: a probabilistic latent state-space model." Journal of Neurophysiology 118, no. 4 (October 1, 2017): 2238–50. http://dx.doi.org/10.1152/jn.00274.2017.

Full text

Abstract:

Motor neurons appear to be activated with a common input signal that modulates the discharge activity of all neurons in the motor nucleus. It has proven difficult for neurophysiologists to quantify the variability in a common input signal, but characterization of such a signal may improve our understanding of how the activation signal varies across motor tasks. Contemporary methods of quantifying the common input to motor neurons rely on compiling discrete action potentials into continuous time series, assuming the motor pool acts as a linear filter, and requiring signals to be of sufficient duration for frequency analysis. We introduce a space-state model in which the discharge activity of motor neurons is modeled as inhomogeneous Poisson processes and propose a method to quantify an abstract latent trajectory that represents the common input received by motor neurons. The approach also approximates the variation in synaptic noise in the common input signal. The model is validated with four data sets: a simulation of 120 motor units, a pair of integrate-and-fire neurons with a Renshaw cell providing inhibitory feedback, the discharge activity of 10 integrate-and-fire neurons, and the discharge times of concurrently active motor units during an isometric voluntary contraction. The simulations revealed that a latent state-space model is able to quantify the trajectory and variability of the common input signal across all four conditions. When compared with the cumulative spike train method of characterizing common input, the state-space approach was more sensitive to the details of the common input current and was less influenced by the duration of the signal. The state-space approach appears to be capable of detecting rather modest changes in common input signals across conditions. NEW & NOTEWORTHY We propose a state-space model that explicitly delineates a common input signal sent to motor neurons and the physiological noise inherent in synaptic signal transmission. This is the first application of a deterministic state-space model to represent the discharge characteristics of motor units during voluntary contractions.

APA, Harvard, Vancouver, ISO, and other styles

34

Pasquini, Cecilia, Francesco Laiti, Davide Lobba, Giovanni Ambrosi, Giulia Boato, and Francesco De Natale. "Identifying Synthetic Faces through GAN Inversion and Biometric Traits Analysis." Applied Sciences 13, no. 2 (January 6, 2023): 816. http://dx.doi.org/10.3390/app13020816.

Full text

Abstract:

In the field of image forensics, notable attention has been recently paid toward the detection of synthetic contents created through Generative Adversarial Networks (GANs), especially face images. This work explores a classification methodology inspired by the inner architecture of typical GANs, where vectors in a low-dimensional latent space are transformed by the generator into meaningful high-dimensional images. In particular, the proposed detector exploits the inversion of the GAN synthesis process: given a face image under investigation, we identify the point in the GAN latent space which more closely reconstructs it; we project the vector back into the image space, and we compare the resulting image with the actual one. Through experimental tests on widely known datasets (including FFHQ, CelebA, LFW, and Caltech), we demonstrate that real faces can be accurately discriminated from GAN-generated ones by properly capturing the facial traits through different feature representations. In particular, features based on facial landmarks fed to a Support Vector Machine consistently yield a global accuracy of above 88% for each dataset. Furthermore, we experimentally prove that the proposed detector is robust concerning routinely applied post-processing operations.

APA, Harvard, Vancouver, ISO, and other styles

35

Wen, Bin, and Jon Bryan Burley. "Expert Opinion Dimensions of Rural Landscape Quality in Xiangxi, Hunan, China: Principal Component Analysis and Factor Analysis." Sustainability 12, no. 4 (February 11, 2020): 1316. http://dx.doi.org/10.3390/su12041316.

Full text

Abstract:

Scholars and planning/design professionals are interested in the quantitative, metric properties influencing the quality and assessment of rural landscape space. These metrics are important for guiding rural planning, design, and construction of cultural rural environments. Respondents and metrics from four sampled villages (Qixin, Hangsha, Yanpai Xi, and Lvdong) in the Xiangxi District of Hunan Province in China were examined, employing statistical principal component analysis and factor analysis methods to understand the identifying properties concerning planning and design features of these rural mountain village landscape spaces. The two approaches reveal different aspects from the same variables. Through factor analysis and rotation, four general dimensions were revealed explaining approximately 62% of the variance: a settlement and environmental axis, an intangible culture axis, a productive landscape axis, and a transportation and public space axis, supporting the standing notion that the variables were ordinated across four dimensions in these mountain villages and occupied an elliptical plane that was different than the predicted space occupied by nearby cites. In contrast, principal component analysis revealed that the variables could be grouped into one latent dimension explaining 48% of the variance and revealing an alternative interpretation and spatial plot of the sites.

APA, Harvard, Vancouver, ISO, and other styles

36

Li, Lianghao, Xiaoming Jin, and Mingsheng Long. "Topic Correlation Analysis for Cross-Domain Text Classification." Proceedings of the AAAI Conference on Artificial Intelligence 26, no. 1 (September 20, 2021): 998–1004. http://dx.doi.org/10.1609/aaai.v26i1.8308.

Full text

Abstract:

Cross-domain text classification aims to automatically train a precise text classifier for a target domain by using labeled text data from a related source domain. To this end, the distribution gap between different domains has to be reduced. In previous works, a certain number of shared latent features (e.g., latent topics, principal components, etc.) are extracted to represent documents from different domains, and thus reduce the distribution gap. However, only relying the shared latent features as the domain bridge may limit the amount of knowledge transferred. This limitation is more serious when the distribution gap is so large that only a small number of latent features can be shared between domains. In this paper, we propose a novel approach named Topic Correlation Analysis (TCA), which extracts both the shared and the domain-specific latent features to facilitate effective knowledge transfer. In TCA, all word features are first grouped into the shared and the domain-specific topics using a joint mixture model. Then the correlations between the two kinds of topics are inferred and used to induce a mapping between the domain-specific topics from different domains. Finally, both the shared and the mapped domain-specific topics are utilized to span a new shared feature space where the supervised knowledge can be effectively transferred. The experimental results on two real-world data sets justify the superiority of the proposed method over the stat-of-the-art baselines.

APA, Harvard, Vancouver, ISO, and other styles

37

Ubbens, Jordan, Mikolaj Cieslak, Przemyslaw Prusinkiewicz, Isobel Parkin, Jana Ebersbach, and Ian Stavness. "Latent Space Phenotyping: Automatic Image-Based Phenotyping for Treatment Studies." Plant Phenomics 2020 (January 20, 2020): 1–13. http://dx.doi.org/10.34133/2020/5801869.

Full text

Abstract:

Association mapping studies have enabled researchers to identify candidate loci for many important environmental tolerance factors, including agronomically relevant tolerance traits in plants. However, traditional genome-by-environment studies such as these require a phenotyping pipeline which is capable of accurately measuring stress responses, typically in an automated high-throughput context using image processing. In this work, we present Latent Space Phenotyping (LSP), a novel phenotyping method which is able to automatically detect and quantify response-to-treatment directly from images. We demonstrate example applications using data from an interspecific cross of the model C4 grass Setaria, a diversity panel of sorghum (S. bicolor), and the founder panel for a nested association mapping population of canola (Brassica napus L.). Using two synthetically generated image datasets, we then show that LSP is able to successfully recover the simulated QTL in both simple and complex synthetic imagery. We propose LSP as an alternative to traditional image analysis methods for phenotyping, enabling the phenotyping of arbitrary and potentially complex response traits without the need for engineering-complicated image-processing pipelines.

APA, Harvard, Vancouver, ISO, and other styles

38

Borade, Jyoti G., Arvind W. Kiwelekar, and Laxman D. Netak. "Automated Grading of PowerPoint Presentations Using Latent Semantic Analysis." Revue d'Intelligence Artificielle 36, no. 2 (April 30, 2022): 305–11. http://dx.doi.org/10.18280/ria.360215.

Full text

Abstract:

Manual grading of students’ work takes a long time and it is stressful. Evaluator may be holistic or analytic, lenient or non-lenient, experienced or inexperienced; which leads to non-uniformity in the assessment. Therefore, it is essential to do the automated grading of students' work to overcome human inadequacies through uniform assessment and also, it reduces workload of human evaluators. A novel automatic grading of students' PowerPoint presentation skills using Latent Semantic Analysis (LSA) is proposed. Program is implemented in python to extract features corresponding to the text appearance, graphics, footer, and hyperlink from the PowerPoint presentations. PowerPoint presentations are represented using feature vectors in the Latent Semantic Space using Singular Value Decomposition (SVD). SVD reveals relationships between features and PowerPoint presentations. The grades for the students' PowerPoint presentations are evaluated by finding Cosine similarity with reference presentations or finding k number of nearest reference presentations. The grades of such reference or nearest presentations are used to grade students' presentations. Kneighbors classifier used to find nearest neighbors. Kneighbors and Cosine Similarity approach give 90.90% and 81.81% accuracy, respectively, while predicting the grades for the students’ PowerPoint presentations.

APA, Harvard, Vancouver, ISO, and other styles

39

Sadiković, Selka, Dina Fesl, and Petar Čolović. "PERSONALITY TYPES ON NEW GROUND: LATENT PROFILE ANALYSIS BASED ON THREE PSYCHOLEXICAL MODELS OF PERSONALITY." Primenjena psihologija 9, no. 1 (April 7, 2016): 41. http://dx.doi.org/10.19090/pp.2016.1.41-61.

Full text

Abstract:

The aim of the research was to determine the number, characteristics, and the level of convergence of personality types extracted in the space of the three psycho-lexical conceptualizations of personality – The Big Five, HEXACO, and The Big Seven. The study was conducted on a sample consisting of 343 participants (55.7% female), aged 18–60 (M = 33.99). The participants completed the IPIP-50 (Big Five model operationalization), IPIP-HEXACO (HEXACO model operationalization) and the BF+2-70 (short version of the questionnaire for assessing seven lexical dimensions in Serbian language) questionnaires. Latent profile analysis was conducted in the space of dimension scores of the three questionnaires. The Bayesian information criterion suggested three-class solution to be optimal in the space of all three questionnaires. Analyzing the structure of latent profiles, the classes within the three models were interpreted as “resilient”, “reserved”, and “maladjusted”. The congruency of classes was analyzed by multiple correspondence analyses, which indicated a high convergence of types in the two-dimensional space. Results indicate a distinct similarity between the extracted profiles with the profiles from previous studies, generally pointing towards the stability of the three big personality prototypes.

APA, Harvard, Vancouver, ISO, and other styles

40

An, Li, Ming-Hsiang Tsou, Brian H. Spitzberg, Dipak K. Gupta, and J. Mark Gawron. "Latent trajectory models for space-time analysis: An application in deciphering spatial panel data." Geographical Analysis 48, no. 3 (February 9, 2016): 314–36. http://dx.doi.org/10.1111/gean.12097.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Yasunaga, Kazuaki, Satoru Yokoi, Kuniaki Inoue, and Brian E. Mapes. "Space–Time Spectral Analysis of the Moist Static Energy Budget Equation." Journal of Climate 32, no. 2 (December 28, 2018): 501–29. http://dx.doi.org/10.1175/jcli-d-18-0334.1.

Full text

Abstract:

Abstract The budget of column-integrated moist static energy (MSE) is examined in wavenumber–frequency transforms of longitude–time sections over the tropical belt. Cross-spectra with satellite-derived precipitation (TRMM-3B42) are used to emphasize precipitation-coherent signals in reanalysis [ERA-Interim (ERAI)] estimates of each term in the budget equation. Results reveal different budget balances in convectively coupled equatorial waves (CCEWs) as well as in the Madden–Julian oscillation (MJO) and tropical depression (TD)-type disturbances. The real component (expressing amplification or damping of amplitude) for horizontal advection is modest for most wave types but substantially damps the MJO. Its imaginary component is hugely positive (it acts to advance phase) in TD-type disturbances and is positive for MJO and equatorial Rossby (ERn1) wave disturbances (almost negligible for the other CCEWs). The real component of vertical advection is negatively correlated (damping effect) with precipitation with a magnitude of approximately 10% of total latent heat release for all disturbances except for TD-type disturbance. This effect is overestimated by a factor of 2 or more if advection is computed using the time–zonal mean MSE, suggesting that nonlinear correlations between ascent and humidity would be positive (amplification effect). ERAI-estimated radiative heating has a positive real part, reinforcing precipitation-correlated MSE excursions. The magnitude is up to 14% of latent heating for the MJO and much less for other waves. ERAI-estimated surface flux has a small effect but acts to amplify MJO and ERn1 waves. The imaginary component of budget residuals is large and systematically positive, suggesting that the reanalysis model’s physical MSE sources would not act to propagate the precipitation-associated MSE anomalies properly.

APA, Harvard, Vancouver, ISO, and other styles

42

Bollon, Jordy, Michela Assale, Andrea Cina, Stefano Marangoni, Matteo Calabrese, Chiara Beatrice Salvemini, Jean Marc Christille, Stefano Gustincich, and Andrea Cavalli. "Investigating How Reproducibility and Geometrical Representation in UMAP Dimensionality Reduction Impact the Stratification of Breast Cancer Tumors." Applied Sciences 12, no. 9 (April 22, 2022): 4247. http://dx.doi.org/10.3390/app12094247.

Full text

Abstract:

Advances in next-generation sequencing have provided high-dimensional RNA-seq datasets, allowing the stratification of some tumor patients based on their transcriptomic profiles. Machine learning methods have been used to reduce and cluster high-dimensional data. Recently, uniform manifold approximation and projection (UMAP) was applied to project genomic datasets in low-dimensional Euclidean latent space. Here, we evaluated how different representations of the UMAP embedding can impact the analysis of breast cancer (BC) stratification. We projected BC RNA-seq data on Euclidean, spherical, and hyperbolic spaces, and stratified BC patients via clustering algorithms. We also proposed a pipeline to yield more reproducible clustering outputs. The results show how the selection of the latent space can affect downstream stratification results and suggest that the exploration of different geometrical representations is recommended to explore data structure and samples’ relationships.

APA, Harvard, Vancouver, ISO, and other styles

43

Li, Ya Xiong, and Deng Pan. "Text Clustering Based on Domain Ontology and Latent Semantic Analysis." Applied Mechanics and Materials 556-562 (May 2014): 3536–40. http://dx.doi.org/10.4028/www.scientific.net/amm.556-562.3536.

Full text

Abstract:

One key step in text mining is the categorization of texts, i.e., to put texts of the same or similar contents into one group so as to distinguish texts of different contents. However, traditional word-frequency-based statistical approaches, such as VSM model, failed to reflect the complicated meaning in texts. This paper ushers in domain ontology and constructs new conceptual vector space model in the pre-processing stage of text clustering, substituting the initial matrix (lexicon-text matrix) in the latent semantic analysis with concept-text matrix. In the clustering analysis stage, this model adopts semantic similarity, partially overcoming the difficulty in accurately and effectively evaluating the degree of similarity of text due to simply taking into account the frequency of words and/or phrases in the text. Experimental results indicate that this method is helpful in improving the result of text clustering.

APA, Harvard, Vancouver, ISO, and other styles

44

GIRJU, ROXANA, and MICHAEL J. PAUL. "Modeling reciprocity in social interactions with probabilistic latent space models." Natural Language Engineering 17, no. 1 (January 2011): 1–36. http://dx.doi.org/10.1017/s1351324910000173.

Full text

Abstract:

AbstractReciprocity is a pervasive concept that plays an important role in governing people's behavior, judgments, and thus their social interactions. In this paper we present an analysis of the concept of reciprocity as expressed in English and a way to model it. At a larger structural level the reciprocity model will induce representations and clusters of relations between interpersonal verbs. In particular, we introduce an algorithm that semi-automatically discovers patterns encoding reciprocity based on a set of simple yet effective pronoun templates. Using the most frequently occurring patterns we queried the web and extracted 13,443 reciprocal instances, which represent a broad-coverage resource. Unsupervised clustering procedures are performed to generate meaningful semantic clusters of reciprocal instances. We also present several extensions (along with observations) to these models that incorporate meta-attributes like the verbs' affective value, identify gender differences between participants, consider the textual context of the instances, and automatically discover verbs with certain presuppositions. The pattern discovery procedure yields an accuracy of 97 per cent, while the clustering procedures – clustering with pairwise membership and clustering with transitions – indicate accuracies of 91 per cent and 64 per cent, respectively. Our affective value clustering can predict an unknown verb's affective value (positive, negative, or neutral) with 51 per cent accuracy, while it can discriminate between positive and negative values with 68 per cent accuracy. The presupposition discovery procedure yields an accuracy of 97 per cent.

APA, Harvard, Vancouver, ISO, and other styles

45

Mora, Niccolò, Federico Cocconcelli, Guido Matrella, and Paolo Ciampolini. "Detection and Analysis of Heartbeats in Seismocardiogram Signals." Sensors 20, no. 6 (March 17, 2020): 1670. http://dx.doi.org/10.3390/s20061670.

Full text

Abstract:

This paper presents an unsupervised methodology to analyze SeismoCardioGram (SCG) signals. Starting from raw accelerometric data, heartbeat complexes are extracted and annotated, using a two-step procedure. An unsupervised calibration procedure is added to better adapt to different user patterns. Results show that the performance scores achieved by the proposed methodology improve over related literature: on average, 98.5% sensitivity and 98.6% precision are achieved in beat detection, whereas RMS (Root Mean Square) error in heartbeat interval estimation is as low as 4.6 ms. This allows SCG heartbeat complexes to be reliably extracted. Then, the morphological information of such waveforms is further processed by means of a modular Convolutional Variational AutoEncoder network, aiming at extracting compressed, meaningful representation. After unsupervised training, the VAE network is able to recognize different signal morphologies, associating each user to its specific patterns with high accuracy, as indicated by specific performance metrics (including adjusted random and mutual information score, completeness, and homogeneity). Finally, a Linear Model is used to interpret the results of clustering in the learned latent space, highlighting the impact of different VAE architectural parameters (i.e., number of stacked convolutional units and dimension of latent space).

APA, Harvard, Vancouver, ISO, and other styles

46

Krishnan, Keerthi, Ryan Kassab, Steve Agajanian, and Gennady Verkhivker. "Interpretable Machine Learning Models for Molecular Design of Tyrosine Kinase Inhibitors Using Variational Autoencoders and Perturbation-Based Approach of Chemical Space Exploration." International Journal of Molecular Sciences 23, no. 19 (September 24, 2022): 11262. http://dx.doi.org/10.3390/ijms231911262.

Full text

Abstract:

In the current study, we introduce an integrative machine learning strategy for the autonomous molecular design of protein kinase inhibitors using variational autoencoders and a novel cluster-based perturbation approach for exploration of the chemical latent space. The proposed strategy combines autoencoder-based embedding of small molecules with a cluster-based perturbation approach for efficient navigation of the latent space and a feature-based kinase inhibition likelihood classifier that guides optimization of the molecular properties and targeted molecular design. In the proposed generative approach, molecules sharing similar structures tend to cluster in the latent space, and interpolating between two molecules in the latent space enables smooth changes in the molecular structures and properties. The results demonstrated that the proposed strategy can efficiently explore the latent space of small molecules and kinase inhibitors along interpretable directions to guide the generation of novel family-specific kinase molecules that display a significant scaffold diversity and optimal biochemical properties. Through assessment of the latent-based and chemical feature-based binary and multiclass classifiers, we developed a robust probabilistic evaluator of kinase inhibition likelihood that is specifically tailored to guide the molecular design of novel SRC kinase molecules. The generated molecules originating from LCK and ABL1 kinase inhibitors yielded ~40% of novel and valid SRC kinase compounds with high kinase inhibition likelihood probability values (p > 0.75) and high similarity (Tanimoto coefficient > 0.6) to the known SRC inhibitors. By combining the molecular perturbation design with the kinase inhibition likelihood analysis and similarity assessments, we showed that the proposed molecular design strategy can produce novel valid molecules and transform known inhibitors of different kinase families into potential chemical probes of the SRC kinase with excellent physicochemical profiles and high similarity to the known SRC kinase drugs. The results of our study suggest that task-specific manipulation of a biased latent space may be an important direction for more effective task-oriented and target-specific autonomous chemical design models.

APA, Harvard, Vancouver, ISO, and other styles

47

Minhas, Shahryar, Peter D. Hoff, and Michael D. Ward. "Inferential Approaches for Network Analysis: AMEN for Latent Factor Models." Political Analysis 27, no. 2 (November 20, 2018): 208–22. http://dx.doi.org/10.1017/pan.2018.50.

Full text

Abstract:

We introduce a Bayesian approach to conduct inferential analyses on dyadic data while accounting for interdependencies between observations through a set of additive and multiplicative effects (AME). The AME model is built on a generalized linear modeling framework and is thus flexible enough to be applied to a variety of contexts. We contrast the AME model to two prominent approaches in the literature: the latent space model (LSM) and the exponential random graph model (ERGM). Relative to these approaches, we show that the AME approach is (a) to be easy to implement; (b) interpretable in a general linear model framework; (c) computationally straightforward; (d) not prone to degeneracy; (e) captures first-, second-, and third-order network dependencies; and (f) notably outperforms ERGMs and LSMs on a variety of metrics and in an out-of-sample context. In summary, AME offers a straightforward way to undertake nuanced, principled inferential network analysis for a wide range of social science questions.

APA, Harvard, Vancouver, ISO, and other styles

48

Friel, Nial, Riccardo Rastelli, Jason Wyse, and Adrian E. Raftery. "Interlocking directorates in Irish companies using a latent space model for bipartite networks." Proceedings of the National Academy of Sciences 113, no. 24 (May 31, 2016): 6629–34. http://dx.doi.org/10.1073/pnas.1606295113.

Full text

Abstract:

We analyze the temporal bipartite network of the leading Irish companies and their directors from 2003 to 2013, encompassing the end of the Celtic Tiger boom and the ensuing financial crisis in 2008. We focus on the evolution of company interlocks, whereby a company director simultaneously sits on two or more boards. We develop a statistical model for this dataset by embedding the positions of companies and directors in a latent space. The temporal evolution of the network is modeled through three levels of Markovian dependence: one on the model parameters, one on the companies’ latent positions, and one on the edges themselves. The model is estimated using Bayesian inference. Our analysis reveals that the level of interlocking, as measured by a contraction of the latent space, increased before and during the crisis, reaching a peak in 2009, and has generally stabilized since then.

APA, Harvard, Vancouver, ISO, and other styles

49

Fukui, Takaya, Seisho Sato, and Akihiko Takahashi. "Style analysis with particle filtering and generalized simulated annealing." International Journal of Financial Engineering 04, no. 02n03 (June 2017): 1750037. http://dx.doi.org/10.1142/s2424786317500372.

Full text

Abstract:

This paper proposes a new approach to style analysis of mutual funds in a general state space framework with particle filtering and generalized simulated annealing (GSA). Specifically, we regard the exposure of each style index as a latent state variable in a state space model and employ a Monte Carlo filter as a particle filtering method, where GSA is effectively applied to estimating unknown parameters. An empirical analysis using data of three Japanese equity mutual funds with six standard style indexes confirms the validity of our method. Moreover, we create fund-specific style indexes to further improve estimation in the analysis.

APA, Harvard, Vancouver, ISO, and other styles

50

Liu, Yingxiang, Wei Ling, Robert Young, Jalal Zia, Trenton T. Cladouhos, and Behnam Jafarpour. "Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations." Energies 15, no. 7 (March 31, 2022): 2555. http://dx.doi.org/10.3390/en15072555.

Full text

Abstract:

This paper presents a latent-space dynamic neural network (LSDNN) model for the multi-step-ahead prediction and fault detection of a geothermal power plant’s operation. The model was trained to learn the dynamics of the power generation process from multivariate time-series data and the effects of exogenous variables, such as control adjustment and ambient temperature. In the LSDNN model, an encoder–decoder architecture was designed to capture cross-correlation among different measured variables. In addition, a latent space dynamic structure was proposed to propagate the dynamics in the latent space to enable prediction. The prediction power of the LSDNN was utilized for monitoring a geothermal power plant and detecting abnormal events. The model was integrated with principal component analysis (PCA)-based process monitoring techniques to develop a fault-detection procedure. The performance of the proposed LSDNN model and fault detection approach was demonstrated using field data collected from a geothermal power plant.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Latent space analysis'

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