Devi Fitrianah
Bina Nusantara University

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Text classification to predict skin concerns over skincare using bidirectional mechanism in long short-term memory Devi Fitrianah; Andre Hangga Wangsa
Computer Science and Information Technologies Vol 3, No 3: November 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/csit.v3i3.p137-147

Abstract

There are numerous types of skincare, each with its own set of benefits based on key ingredients. This may be difficult for beginners who are purchasing skincare for the first time due to a lack of knowledge about skincare and their own skin concerns. Hence, based on this problem, it is possible to find out the right skin concern that can be handled in each skincare product automatically by multi-class text classification. The purpose of this research is to build a deep learning model capable of predicting skin concerns that each skincare product can treat. By comparing the performance and results of predicting the correct skin condition for each skincare product description using both long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM), The best results are given by Bi-LSTM, which has an accuracy score of 98.04% and a loss score of 19.19%. Meanwhile, LSTM results have an accuracy score of 94.12% and a loss score of 19.91%.
Ozone Gases Value Forecasting Using Encoder-Decoder LSTM Model Ni Ketut Intan Rahayu*; Devi Fitrianah; Elvin Elvin; Tannuru Marthamurtadh
Riwayat: Educational Journal of History and Humanities Vol 6, No 3 (2023): Social, Political, and Economic History
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/jr.v6i3.34435

Abstract

Climate change, as one of the impacts of global warming, has several consequences for the sustainability of living beings on Earth. It is necessary to monitor the trend of climate change. One way to monitor seasonal patterns of change is by analyzing the ozone content in the air. In addition to being an indicator of climate change, predicting the ozone gas content in the air is important because ozone gas has a direct impact on living organisms. By predicting the ozone gas content, it is hoped that preventive measures can be taken to prevent the adverse effects of ozone gas in the air. In the case of predicting ozone gases, there may be certain patterns that only become apparent over time, such as seasonal variations or long-term trends. A model that can capture these long-term dependencies will be better equipped to accurately predict ozone gas levels in the future. In this experiment, we proposed the use of Encoder-Decoder LSTM to predict ozone gas values.
A Study on Enhanced Spatial Clustering Using Ensemble Dbscan and Umap to Map Fire Zone in Greater Jakarta, Indonesia Silviya Hasana; Devi Fitrianah
Jurnal Riset Informatika Vol. 5 No. 3 (2023): June 2023
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (724.615 KB) | DOI: 10.34288/jri.v5i3.234

Abstract

This research investigated ensemble clustering algorithms and dimensionality reduction for fire zone mapping, specifically DBSCAN + UMAP. We evaluated six clustering methods: DBSCAN, ensemble DBSCAN, DBSCAN + UMAP, ensemble DBSCAN + UMAP, HDBSCAN and Gaussian Mixture Model (GMM). We evaluated our results based on the Silhouette Score and the Davies-Bouldin (DB) index, emphasizing handling irregular cluster shapes, smaller clusters and resolving incompact clusters. Our findings suggested that ensemble DBSCAN + UMAP outperformed five other methods with zero noise clusters indicating clustering results are resistant to outliers, leading to a clearer identification of fire-prone areas, a high Silhouette Score of 0.971, indicating accurate cluster separation of distinct areas of potential fire hazards and an exceptionally low DB Index of 0.05 that indicates compact clusters to identify well-defined and geographically concentrated areas prone to fire hazards. Our findings contribute to the advanced techniques for minimizing the impacts of fires and improving fire hazard assessments in Indonesia.