422 research outputs found
asl-epfl/asl-it-2021: Adaptive Social Learning (IT 2021)
No full textThis code can be used to generate simulations similar to Figs. 1, 2, 3, 4, 6, 7, 8, 9, 10, 12 and 13 in the following paper:
Virginia Bordignon, Vincenzo Matta, and Ali H. Sayed, "Adaptive social learning,'' in IEEE Transactions on Information Theory, 2021. DOI: 10.1109/TIT.2021.3094633
Figs. 1 and 2 are generated executing file 'figs1_2.py'.
Fig. 3 is generated executing file 'fig3.py'.
Fig. 4 is generated executing file 'fig4.py'.
Figs. 6-10 are generated executing file 'figs6_7_8_9_10.py'.
Figs. 12 and 13 are generated executing file 'figs12_13.py'.
Please note that the code is not generally perfected for performance, but is rather meant to illustrate certain results from the paper. The code is provided as-is without guarantees.
July 2021 (Author: Virginia Bordignon
asl-epfl/asl-eusipco2020: Adaptation in Online Social Learning (EUSIPCO 2020)
No full textThis code can be used to generate simulations similar to Figs. 1, 2, 3, 4 and 5 in the following paper:
Virginia Bordignon, Vincenzo Matta, and Ali H. Sayed, "Adaptation in online social learning,'' Proc. EUSIPCO, pp. 1-5, Amsterdam, The Netherlands, August 2020. DOI:10.23919/Eusipco47968.2020.9287445
Fig. 1 is generated executing file 'codefig1.py'.
Figs. 2, 3 and 4 are generated executing file 'codefig234.py'.
Please note that the code is not generally perfected for performance, but is rather meant to illustrate certain results from the paper. The code is provided as-is without guarantees.
July 2020 (Author: Virginia Bordignon
asl-epfl/social_learning_under_randomized_collaborations_isit2022: v1.0.0-isit2022
No full text<p>This notebook can be used to generate simulations of the following paper:</p>
<p>Y. İnan, M. Kayaalp, E. Telatar and A. H. Sayed, "Social Learning under Randomized Collaborations," Proc. IEEE International Symposium on Information Theory (ISIT), Espoo, Finland, 2022, pp. 115-120, doi: 10.1109/ISIT50566.2022.9834621.</p>
<p>Please note that the code is not generally perfected for performance, but is rather meant to illustrate certain results from the paper. The code is provided as-is without guarantees.</p>
<p>Author: Y. İnan</p>
ASL Stories by Doug Bullard
No full textDoug Bullard, deaf author of Islay, in this 1 hour 11 minute video, tells stories such as Teaching ASL, Interpreters, Bear Hunting, Life in Alaska, Travel Stories, History of Women and Hitch-hiking. Stories range from 1 minute to 29 minutes. No voicing or captioning.https://digitalcommons.unf.edu/asleimats/1015/thumbnail.jp
ASL Rhyme, Rhythm, and Phonological Awareness for Deaf Children
No full textThe author, who is of multigenerational Deaf heritage, provides a review of the literature on spoken and signed rhyme, rhythm, and phonological awareness used with young children. While a foundation of knowledge has been built with early language approaches in spoken language, little is known about parallel forms of these approaches in American Sign Language (ASL). ASL rhyme, rhythm, and phonological awareness have historically been absent from early childhood classrooms that serve Deaf children. The author explores why this is the case and draws upon historical events to provide answers. An autoethnographic account of the author’s experience with early language approaches as a Deaf child, adult, and early childhood educator is shared. Some directions for future research include examining the effectiveness of ASL rhyme, rhythm, and phonological awareness in improving language and literacy outcomes
Ships Observing Marine Climate: a catalogue of the VOS participating in the VSOP-NA
No full textOur present knowledge of the marine climate, as represented by data sets such as COADS (Woodruff et al., 1987), is based on meteorological observations from the Voluntary Observing Ships (VOS). Because the VOS are merchant ships, rather than specially designed meteorological platforms, errors and biases exist in the data. However there is little information readily available to the climatologist either on the nature of the VOS fleet or on the observing practises which are used. This report, describing the forty-six ships that participated in the Voluntary Observing Ships' Special Observing Project - North Atlantic (VSOP-NA), therefore serves two purposes:(i) it provides a reference document to aid analysis of the VSOP-NA data set,(ii) it gives a detailed description of a subset of the VOS, which will be of value in the interpretation of marine climate data sets.This report is in two parts, Part 1 is an overall summary of the ship characteristics, Part 2 is a ship by ship description. The next section will briefly describe the VSOP-NA project, followed by a summary of the characteristics of the VSOP-NA ships (Section 3). Since these ships were specially selected (Section 2.2), the degree to which they are representative of the whole VOS fleet will be carefully considered. The meteorological instrumentation used by the VOS varies depending on which meteorological agency recruited the ships. That used on the chosen VSOP-NA ships is typical of VOS recruited by the countries bordering the North Atlantic, and will be described in Section 4. Section 5 is a summary of Part 1 of the report.Part 2 presents the VSOP-NA ship catalogue. This includes, for each ship, diagrams of the layout (indicating in particular the exposure of the sensors), a summary of the geographical positions at which observations were obtained, and details of the instrumentation used.<br/
COHST and Wavelet Features Based Static ASL Numbers Recognition
No full textAbstractBridging communication gap between the deaf and dumb people with the common man is a big challenge. A sign language recognition system could provide an opportunity for the deaf and dumb to communicate with non-signing people without the need for an interpreter. Research in the area of Sign language recognition has become very significant due to various challenges faced while capturing of the sign. Not a single efficient methodology or algorithm is developed which overcomes all the difficulties and recognizes all the signs with cent percent accuracy. This paper proposes two new feature extraction techniques of Combined Orientation Histogram and Statistical (COHST) Features and Wavelet Features for recognition of static signs of numbers 0 to 9, of American Sign Language (ASL). The system performance is measured by extracting four different features of Orientation Histogram, Statistical Measures, COHST Features and Wavelet Features for training and recognition of ASL numbers individually using neural network. It is observed that COHST method forms a strong feature than the individual Orientation Histogram and Statistical Features giving higher average recognition rate. Of all the System designed for static ASL numbers recognition, Wavelet features based system gives the best performance with maximum average recognition rate of 98.17%
Forced Transitions: Learning ASL In A Virtual Environment
No full textEngagement with native language models is essential for second language acquisition. Social distancing mandates made this interaction nearly impossible for students learning American Sign Language (ASL), at a small rural university in western Oregon. COVID-19 brought with it many challenges, not the least of which was a hurried transition from face-to-face to online learning. The author found that some courses degraded in content and instruction when shifting to an online platform. Without access to community events where native language models were present, ASL students had less opportunities for incidental learning, legitimate peripheral participation, and connection within Deaf communities of practice
asl-epfl/nbnb_eusipco2023: Social Learning with Non-Bayesian Local Updates
No full text<p>This code can be used to generate simulations similar to Fig. 1 in the following paper:</p>
<p>V. Bordignon, M. Kayaalp, V. Matta, and A. H. Sayed, "Social learning with non-Bayesian local updates,'' Proc. EUSIPCO, pp. 1-5, Helsinki, Finland, Sep. 2023.</p>
<p>The images used in Fig. 1 are generated executing file 'main.py'.</p>
<p>Please note that the code is not generally perfected for performance, but is rather meant to illustrate certain results from the paper. The code is provided as-is without guarantees.</p>
<p>Jul 2023 (Author: Virginia Bordignon)</p>
asl-epfl/graph_influence_icassp2020: Learning Graph Influence from Social Interactions
No full textThis code can be used to generate simulations similar to Fig. 1 in the following paper:
Vincenzo Matta, Virginia Bordignon, Augusto Santos, and Ali H. Sayed, ``Learning graph influence from social interactions,'' Proc. IEEE ICASSP, Barcelona, Spain, May 2020. DOI: ICASSP40776.2020.9054244
Fig. 1 is generated executing file 'codefig1.py'.
Please note that the code is not generally perfected for performance, but is rather meant to illustrate certain results from the paper. The code is provided as-is without guarantees.
July 2020 (Author: Virginia Bordignon
- …
