Filters








437,050 Hits in 4.5 sec

Understanding Hidden Memories of Recurrent Neural Networks [article]

Yao Ming and Shaozu Cao and Ruixiang Zhang and Zhen Li and Yuanzhe Chen and Yangqiu Song and Huamin Qu
2017 arXiv   pre-print
We then co-cluster hidden state units and words based on the expected response and visualize co-clustering results as memory chips and word clouds to provide more structured knowledge on RNNs' hidden states  ...  We also propose a glyph-based sequence visualization based on aggregate information to analyze the behavior of an RNN's hidden state at the sentence-level.  ...  The authors also wish to thank the domain experts who participated in the studies and Miss Yuehan Liu who helped record the video.  ... 
arXiv:1710.10777v1 fatcat:b2dj2pjfizf7ldbrmokkeretvy

Task-Oriented Optimal Sequencing of Visualization Charts [article]

Danqing Shi, Yang Shi, Xinyue Xu, Nan Chen, Siwei Fu, Hongjin Wu, Nan Cao
2019 arXiv   pre-print
detection, and cluster analysis.  ...  We conducted one case study and two user studies to evaluate the effectiveness of our method under the application scenarios of visualization demonstration, sequencing charts for reasoning analysis results  ...  ACKNOWLEDGMENTS We would like to thank all visualization experts and users for participating our studies and interviews.  ... 
arXiv:1908.02502v1 fatcat:dmlfzbemznhglg6fwsulc5g45e

Using sequence analysis to visualize and validate model transitions

Janne Salonen, Jyrki Möttönen, Heikki Tikanmäki, Tapio Nummi
2020 International Journal of Microsimulation  
Data and Code Availability Data and code have been provided to the journal and is available from its website.  ...  state is added to the sequence), and deletion (a state is deleted from the sequence).  ...  Both R packages offer analysis and visualization tools for either state or event sequences. Appendix A.1 gives an example of the R programming code.  ... 
doi:10.34196/ijm.00218 fatcat:p5ml5pwrivfdvpwsytjakve6ly

Treelink: data integration, clustering and visualization of phylogenetic trees

Christian Allende, Erik Sohn, Cedric Little
2015 BMC Bioinformatics  
File support includes the most popular formats such as newick and csv. Exporting visualizations as images, cluster outputs and genomic sequences is supported.  ...  Genomic and proteonomic sequences can also be linked to the tree and extracted from internal and external nodes.  ...  Acknowledgements Thanks to Héctor Allende Olivares for helping with the mathematical explanations of the clustering algorithm.  ... 
doi:10.1186/s12859-015-0860-1 pmid:26714661 pmcid:PMC4696249 fatcat:42pxj2syrvckbc5woh3hwzaz2a

Visualization and Exploration of Temporal Trend Relationships in Multivariate Time-Varying Data

Teng-Yok Lee, Han-Wei Shen
2009 IEEE Transactions on Visualization and Computer Graphics  
Based on the beginning and ending times of the trends, their temporal relationships can be modeled as a state machine representing the trend sequence.  ...  We present a new algorithm to explore and visualize multivariate time-varying data sets.  ...  This work is supported by NSF ITR Grant ACI-0325934, NSF RI Grant CNS-0403342, NSF Career Award CCF-0346883, and DOE SciDAC grant DE-FC02-06ER25779.  ... 
doi:10.1109/tvcg.2009.200 pmid:19834209 fatcat:v4jufjoaanck3bs6wjwnuiz56y

Exploring Flow, Factors, and Outcomes of Temporal Event Sequences with the Outflow Visualization

K. Wongsuphasawat, D. Gotz
2012 IEEE Transactions on Visualization and Computer Graphics  
This paper describes the Outflow visualization technique, designed to (1) aggregate multiple event sequences, (2) display the aggregate pathways through different event states with timing and cardinality  ...  Users can interactively explore the paths via which entities arrive and depart various states. This screenshot shows a visualization of Manchester United's 2010-2011 soccer season.  ...  ACKNOWLEDGMENTS The authors wish to thank Charalambos (Harry) Stavropoulos, Robert Sorrentino and Jimeng Sun for their help and suggestions.  ... 
doi:10.1109/tvcg.2012.225 pmid:26357175 fatcat:kqo75j2lprgvfj7zw3hfjq5qqe

MotionExplorer: Exploratory Search in Human Motion Capture Data Based on Hierarchical Aggregation

Jurgen Bernard, Nils Wilhelm, Bjorn Kruger, Thorsten May, Tobias Schreck, Jorn Kohlhammer
2013 IEEE Transactions on Visualization and Computer Graphics  
Based on an overview-first type visualization, users are able to search for interesting sub-sequences of motion based on a query-by-example metaphor, and explore search results by details on demand.  ...  To address this need, we developed MotionExplorer together with domain experts as an exploratory search system based on interactive aggregation and visualization of motion states as a basis for data navigation  ...  We appreciated the collaborative work and the bilateral exchange in knowledge and expertise during the complete duration of this design study.  ... 
doi:10.1109/tvcg.2013.178 pmid:24051792 fatcat:emjtfkzp5fevrlnzxwso3z3ovu

Improving Disease Prediction using Shallow Convolutional Neural Networks on Metagenomic Data Visualizations based on Mean-Shift Clustering Algorithm

Hai Thanh Nguyen, Toan Bao, Huong Hoang, Trung Phuoc, Nghi C.
2020 International Journal of Advanced Computer Science and Applications  
In this study, we introduce a visualization method based on Mean-shift algorithm which enables us to observe high-dimensional data via images exhibiting clustered features by the clustering method.  ...  Data Visualization is a crucial technique in data analysis to explore and find patterns in data.  ...  OTUs are generated by clustering sequences according to a computed distance between two similar sequences and a threshold.  ... 
doi:10.14569/ijacsa.2020.0110607 fatcat:jm2u2i2fwjg4zosshza3srnume

Use of State Sequence Analysis in Pharmacoepidemiology: A Tutorial

Jacopo Vanoli, Consuelo Rubina Nava, Chiara Airoldi, Andrealuna Ucciero, Virginio Salvi, Francesco Barone-Adesi
2021 International Journal of Environmental Research and Public Health  
to identify sequence patterns, the use of complexity measures for sequence patterns, the graphical visualization of sequences, and the use of SSA in predictive models.  ...  In this paper, we provide an educational primer of the most important learning concepts and methods of SSA, including measurement of dissimilarities between sequences, the application of clustering methods  ...  Sections 4 and 5 introduce complexity measures and tools for graphical visualization. Section 6 shows how to include clusters obtained by SSA into predictive models.  ... 
doi:10.3390/ijerph182413398 pmid:34949007 pmcid:PMC8705850 fatcat:dmy2jlj74nas3gz2ich3wnomvu

Visualizing Changes in Strategy Use across Attempts via State Diagrams: A Case Study

Deirdre Kerr
2016 International Journal of Computer Games Technology  
attempts at the same level, and state transition diagrams to visualize the strategy sequences identified by the sequence mining.  ...  In the educational video game used in this case study, cluster analysis successfully identified 15 different in-game strategies.  ...  This material is based upon work supported by the Institute of Education Sciences, US Department of Education, through Grant R305C080015 to the National Center for Research on Evaluation, Standards, and  ... 
doi:10.1155/2016/8492312 fatcat:rd3b37dlzfbh7cy7psjs4yoe6q

Role of route previewing strategies on climbing fluency and exploratory movements

Ludovic Seifert, Romain Cordier, Dominic Orth, Yoan Courtine, James L. Croft, Etsuro Ito
2017 PLoS ONE  
Using cluster analysis we identified four clusters of gaze behavior during route previewing depending on route preview duration, number of scan paths, fixations duration, ascending, zigzagging, and sequence-of-blocks  ...  , ascending, zigzagging, and sequence-of-blocks) they used.  ...  Cluster 4 had shorter duration of route preview and less visual fixations on holds compared to cluster 2, while cluster 2 spent less time previewing in sequences of blocks.  ... 
doi:10.1371/journal.pone.0176306 pmid:28441425 pmcid:PMC5404847 fatcat:jlrrvxhxh5ed3fgomehoajpbcm

Evaluating the Effects of Missing Values and Mixed Data Types on Social Sequence Clustering Using t-SNE Visualization

Alina Lazar, Ling Jin, C. Anna Spurlock, Kesheng Wu, Alex Sim, Annika Todd
2019 Journal of Data and Information Quality  
In social science research, time series clustering is used to study the spans of individuals' life trajectories in the form of sequence analysis [Bras et al. 2010; Schumacher et al. 2012; Widmer and Ritschard  ...  on the overall life trajectory of a given individual's characteristics and the pathway through which one arrives at a given state, decision or behavior.  ...  However, he only studied gaps of multiple states occurring in the middle of the sequences and not at the beginning or the end.  ... 
doi:10.1145/3301294 dblp:journals/jdiq/LazarJSWST19 fatcat:eja3npf4dbccddp3q6cnlejus4

Recognizing People's Faces: from Human to Machine Vision

Massimo Tistarelli, Manuele Bicego, Enrico Grosso
2006 2006 9th International Conference on Control, Automation, Robotics and Vision  
As confirmed by recent neurophysiological studies, the use of dynamic information is extremely important for humans in visual perception of biological forms and motion.  ...  The number of states (or facial expressions) are automatically determined from the data by unsupervised clustering of expressions of faces in the video.  ...  ACKNOWLEDGMENT This work was supported by funds from the European Union (European Network of Excellence Biosecure) and from funds of the Italian Ministry of Research.  ... 
doi:10.1109/icarcv.2006.345481 dblp:conf/icarcv/TistarelliBG06 fatcat:tifp5iuvbbegtea6desf4qlb2y

Exploring the efficiency of users' visual analytics strategies based on sequence analysis of eye movement recordings

A. Çöltekin, S.I. Fabrikant, Martin Lacayo
2010 International Journal of Geographical Information Science  
., speed) of users can be characterized by specific display interaction event sequences, and whether studying user strategies could be employed to improve the (interaction) design of the dynamic displays  ...  The approach systematically studies users' visual interaction strategies when using highly interactive interfaces.  ...  Acknowledgments This study was partially funded by the Swiss National Fund (award numbers 200021_120434/1: Ç öltekin and 200021-113745: Fabrikant) and the US Fulbright -Swiss Scholarship Program.  ... 
doi:10.1080/13658816.2010.511718 fatcat:u2ddv6ymt5hbjnmxkllrmqszhe

Dynamic face recognition: From human to machine vision

Massimo Tistarelli, Manuele Bicego, Enrico Grosso
2009 Image and Vision Computing  
As confirmed by recent neurophysiological studies, the use of dynamic information is extremely important for humans in visual perception of biological forms and motion.  ...  The number of states (or facial expressions) are automatically determined from the data by unsupervised clustering of expressions of faces in the video.  ...  earlier studies on the relation between face recognition and visual motion processing [1] .  ... 
doi:10.1016/j.imavis.2007.05.006 fatcat:t5uhkdvwnreuraabqy4bn25fje
« Previous Showing results 1 — 15 out of 437,050 results