Claim Missing Document
Check
Articles

Found 24 Documents
Search

Improving Indonesian Named Entity Recognition for Domain Zakat Using Conditional Random Fields Widiyanti, Nur Febriana; Sukmana, Husni Teja; Hulliyah, Khodijah; Khairani, Dewi; Oh, Lee Kyung
JOIN (Jurnal Online Informatika) Vol 8 No 2 (2023)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v8i2.898

Abstract

In Indonesia, where the majority of the population is Muslim, one of the obligations of a Muslim is zakat. To reduce illiteracy about zakat among Muslims, they need to have access to basic information about it. In order to facilitate the acquisition of this information, this study utilized named entity recognition (NER) and defined 12 named entity classes for the zakat domain, including the pillars of Islam, various types of zakat, and zakat management institutions. The Conditional Random Fields method was used for testing Indonesian-NER in three scenarios. In the specific context of the Zakat domain, NER can extract information about organizations, individuals, and locations involved in collecting and distributing Zakat funds. This information can improve the Zakat system’s efficiency and transparency and support research and analysis on Zakat-related topics. The average performance evaluation of the Indonesian-NER model showed a precision of 0.902, recall of 0.834, and an F1-score of 0.867.
Enhancing Speech-to-Text and Translation Capabilities for Developing Arabic Learning Games: Integration of Whisper OpenAI Model and Google API Translate Khairani, Dewi; Rosyadi, Tabah; Arini, Arini; Rahmatullah, Imam Luthfi; Antoro, Fauzan Farhan
JURNAL TEKNIK INFORMATIKA Vol. 17 No. 2: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v17i2.41240

Abstract

This study tackles language barriers in computer-mediated communication by developing an application that integrates OpenAI’s Whisper ASR model and Google Translate machine translation to enable real-time, continuous speech transcription and translation and the processing of video and audio files. The application was developed using the Experimental method, incorporating standards for testing and evaluation. The integration expanded language coverage to 133 languages and improved translation accuracy. Efficiency was enhanced through the use of greedy parameters and the Faster Whisper model. Usability evaluations, based on questionnaires, revealed that the application is efficient, effective, and user-friendly, though minor issues in user satisfaction were noted. Overall, the Speech Translate application shows potential in facilitating transcription and translation for video content, especially for language learners and individuals with disabilities. Additionally, this study introduces an Arabic learning game incorporating an Artificial Neural Network using the CNN algorithm. Focusing on the “Speaking” skill, the game applies to voice and image extraction techniques, achieving a high accuracy rate of 95.52%. This game offers an engaging and interactive method for learning Arabic, a language often considered challenging. The incorporation of Artificial Neural Network technology enhances the effectiveness of the learning game, providing users with a unique and innovative language learning experience. By combining voice and image extraction techniques, the game offers a comprehensive approach to enjoyably improving Arabic speaking skills.
Study of Bitcoin Market Efficiency Using Runs Test and Autocorrelation Sukmana, Husni Teja; Khairani, Dewi
Journal of Current Research in Blockchain Vol. 1 No. 1 (2024): Regular Issue June
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jcrb.v1i1.9

Abstract

This paper presents a comprehensive statistical analysis of Bitcoin's daily returns, focusing on their unique characteristics and implications for financial modeling and market behavior. The descriptive statistics reveal a mean daily return of 0.001912 and a standard deviation of 0.044069, highlighting high volatility. The skewness of -1.297892 and kurtosis of 22.099740 indicate a left-skewed, leptokurtic distribution with frequent extreme price movements. The Jarque-Bera test statistic of 95428.68, with a p-value of 0.0, strongly rejects the null hypothesis of normality, suggesting that traditional financial models assuming normally distributed returns may be inappropriate for Bitcoin. The ADF test statistic of -12.303, with a p-value of 7.36e-23, confirms the stationarity of Bitcoin's daily returns, validating their suitability for time series analysis techniques such as ARIMA and GARCH models. Autocorrelation analysis uncovers significant short-term predictability in Bitcoin returns, challenging the weak form of market efficiency, though this predictability diminishes over time. The Runs Test, with a z-score of 2.56 and a p-value of 0.01, further supports the presence of short-term non-random behavior. Additional visualizations, including the daily closing price plot, histogram, and boxplot of daily returns, illustrate the high volatility and substantial variability in Bitcoin's market behavior. The findings underscore the need for specialized risk management strategies and financial models tailored to the cryptocurrency market's unique dynamics. While Bitcoin offers opportunities for high returns, it also poses significant risks due to its volatile nature and frequent extreme price movements. Future research should explore advanced models accounting for heavy tails and volatility clustering and examine the impact of external factors such as regulatory changes and macroeconomic events on Bitcoin's statistical properties. Understanding these characteristics is crucial for informed investment decisions and effective trading strategies in the evolving cryptocurrency market.
Analisis Peningkatan Kemampuan Representasi Matematis Siswa SMA Ditinjau dari Perbedaan Gender Izwita Dewi; Sahat Saragih; Dewi Khairani
Didaktik Matematika Vol 4, No 2 (2017): Jurnal Didaktik Matematika
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/jdm.v4i2.8863

Abstract

Mathematical representation is one of the mathematical higher order thinking skills, as a tool or way of thinking in communicating mathematical ideas. Referring to a research about the inconsistency of a mathematical communication profile involving gender differences and the phenomenon of more female students than men right now, there appears to be an allegation that there is a connection between gender differences and students mathematical representation. The purpose of this study is to analyze the improvement of students' mathematical representation capability in terms of gender differences. Subjects in this research were students of class X of High School in Medan, Indonesia, consisting of 13 men and 19 women. The research instrument is a mathematical representation test consisting of 4 questions. Data analysis to find out how the category of improvement of students mathematical representation, using index of N-gain. The results of the research are: (1) the improvement of mathematical representation ability in the lower and middle categories of male students is higher than female students, (2) there is no male students have high category mathematical representation, but there are female students have high category mathematical representation abilities, and (3) the ability of representation to make mathematical models and explain the verbal language of male students is higher than female students. While the representational ability of making tables and drawing female students is higher than male students. The implication of the research is needs to do deeper research to see the relationship of mathematical representation ability with the students' mathematical ability profile.