Claim Missing Document
Check
Articles

Teknologi Kecerdasan Buatan Untuk Mengembangkan Desain Motif Batik Kontemporer Rianto Rianto; Enny Itje Sela; Nur Wening
Jurnal ABDI RAKYAT Vol. 1 No. 2 (2024): JURNAL ABDI RAKYAT
Publisher : Universitas Teknologi Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46923/jar.v1i2.448

Abstract

Artificial intelligence technology in producing contemporary batik motif designs is an innovative phase in the creative industry. The development of technology, Natural Language Processing, allows text to be translated into images, providing an excellent opportunity to accelerate the design process while enriching creative ideas. This community service program aims to train batik artisans in adopting information technology, especially artificial intelligence, to create new, attractive motif designs. The training includes using an AI-based platform and design transfer techniques to fabric media. The result of this activity is a contemporary batik motif that targets millennials with their distinctive style. This technology provides two main advantages: 1) time efficiency in design creation and 2) broad creative inspiration through automatic exploration of motif data. Both of these advantages show that the application of artificial intelligence in batik design supports innovation and competitiveness in the modern market.
Application of The Fuzzy Inference System Method to Predict The Number of Weaving Fabric Production Tundo Tundo; Enny Itje Sela
IJID (International Journal on Informatics for Development) Vol. 7 No. 1 (2018): IJID June
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2018.07105

Abstract

In this study discusses the application of fuzzy logic in solving production problems using the Tsukamoto method and the Sugeno method. The problem that is solved is how to determine the production of woven fabric when using three variables as input data, namely: stock, demand and inventory of production costs. The first step is to solve the problem of woven fabric production using the Tsukamoto method which is to determine the input variables and output variables which are firm sets, the second step is to change the input variable into a fuzzy set with the fuzzification process, then the third step is processing the fuzzy set data with the maximum method. And the last or fourth step is to change the output into a firm set with the defuzzification process with a weighted average method, so that the desired results will be obtained in the output variable. The solution to the production problem using the Sugeno method is almost the same as using the Tsukamoto method, it's just that the system output is not a fuzzy set, but rather a constant or a linear equation. The difference between the Tsukamoto Method and the Sugeno Method is in consequence. The Sugeno method uses constants or mathematical functions of the input variables. From the calculation data of the production of Mlaki Wanarejan Utara Pemalang woven fabric according to Tsukamoto's method in March 2017 using Weka's rule obtained 343 woven fabrics in meters, while using the Sugeno method obtained 371 woven fabrics in meters. While according to Tsukamoto's method in March 2017 using monotonous rules obtained 313 woven fabrics in meters, then using the Sugeno method obtained 321 woven fabrics in meters, while according to the company's production data in March 2017 produced 340 woven fabrics in meters, then from the analysis direct comparison with the original data in the company can be concluded that the method that is closest to the truth value is the production obtained by processing data using the Tsukamoto method using the Weka rules.
Debtor Eligibility Prediction Using Deep Learning with Chatbot-Based Testing Noviania, Reski; Sela, Enny Itje; Latumakulita, Luther Alexander; Sentinuwo, Steven R.
Knowledge Engineering and Data Science
Publisher : citeus

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Predicting debtor eligibility is essential for effective risk management and minimizing lousy credit risks. However, financial institutions face challenges such as imbalanced data, inefficient feature selection, and limited user accessibility. This study combines Recursive Feature Elimination (RFE) and Deep Learning (DL) to improve prediction accuracy. It integrates a chatbot interface for user-friendly testing. RFE effectively identifies critical features, while the DL model achieves a validation accuracy of 97.62%, surpassing previous studies with less comprehensive methodologies. The chatbot's novel design not only ensures accessibility but also enhances user engagement through flexible input options, such as approximate values, enabling non experts to interact seamlessly with the system. For financial institutions, this chatbot based testing approach offers practical benefits by streamlining debtor evaluation processes, reducing dependency on manual assessments, and providing consistent, scalable, and efficient solutions for credit risk management. It allows institutions to handle inquiries outside business hours, ensuring a continuous service flow. Furthermore, the system’s flexibility supports better customer interaction, increasing trust and transparency. By combining advanced machine learning with accessible interfaces, this study offers a scalable solution to improve the precision and practicality of debtor eligibility assessments, making it a valuable tool for modern financial institutions.