TY - GEN
T1 - Sign language system for Bahasa Indonesia (Known as SIBI) recognizer using TensorFlow and long short-term memory
AU - Halim, Kustiawanto
AU - Rakun, Erden
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2019/1/17
Y1 - 2019/1/17
N2 - SIBI is used formally as a Sign Langnage System for Bahasa Indonesia. SIBI follows Bahasa Indonesia's grammatical structure, which makes it a unique and complex Sign Language System. The state of current research in SIBI is that it is possible to translate the alphabet, root words and numbers to text. This research focuses in recognizing inflectional words, which are root words and combination of prefix, infix and suffix. By separating the root words, prefix, infix and suffix, it was possible to use minimal feature sets. SIBI sequence data contains temporal dependencies, therefore Long Short-Term Memory (LSTM) is chosen as the machine learning model to use on this problem. The entire sequence of feature sets based on the SIBI inflectional word gestures is used as input TensorFlow is used as development framework to make sure model can be easily deployed to a variety of devices, including smartphone». The best results were obtained using a 2-layer LSTM with 96.15% of accuracy for root words. The same model obtained an accuracy score of 78-38% with Inflectional words. The model, however, still struggles in recognizing prefixes and suffixes correctly.
AB - SIBI is used formally as a Sign Langnage System for Bahasa Indonesia. SIBI follows Bahasa Indonesia's grammatical structure, which makes it a unique and complex Sign Language System. The state of current research in SIBI is that it is possible to translate the alphabet, root words and numbers to text. This research focuses in recognizing inflectional words, which are root words and combination of prefix, infix and suffix. By separating the root words, prefix, infix and suffix, it was possible to use minimal feature sets. SIBI sequence data contains temporal dependencies, therefore Long Short-Term Memory (LSTM) is chosen as the machine learning model to use on this problem. The entire sequence of feature sets based on the SIBI inflectional word gestures is used as input TensorFlow is used as development framework to make sure model can be easily deployed to a variety of devices, including smartphone». The best results were obtained using a 2-layer LSTM with 96.15% of accuracy for root words. The same model obtained an accuracy score of 78-38% with Inflectional words. The model, however, still struggles in recognizing prefixes and suffixes correctly.
KW - LSTM
KW - Recurrent Neural Network
KW - SIBI
KW - Sign Language
KW - Smartphone
KW - TensorFlow
UR - http://www.scopus.com/inward/record.url?scp=85062406686&partnerID=8YFLogxK
U2 - 10.1109/ICACSIS.2018.8618134
DO - 10.1109/ICACSIS.2018.8618134
M3 - Conference contribution
AN - SCOPUS:85062406686
T3 - 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
SP - 403
EP - 407
BT - 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
Y2 - 27 October 2018 through 28 October 2018
ER -