Elly Warni’s research while affiliated with Hasanuddin University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (11)


Deep Learning Approach in Seismology: Enhancing Earthquake Forecasting using K-Means Clustering and LSTM Networks
  • Article

January 2025

·

1 Read

Journal of Information and Communication Technology

·

·

Elly Warni

·

[...]

·

Muhammad Alwi Kayyum

Located in the subduction zone of four tectonic plates, the high occurrence of seismic events is a severe threat in Indonesia. Mitigating the adverse effects of such disasters is essential to forecast the likelihood of future earthquakes. Consequently, developing a robust method of forecasting future earthquakes is critical to facilitate prevention and mitigation efforts. A reliable earthquake prediction method is necessary to reduce the after-effects to the greatest extent possible. This study utilises historical seismic and proposes innovative data pre-processing methods using K-means clustering to build a Long Short-Term Memory (LSTM) model for earthquake forecasting to overcome high-disparity locations. Four LSTM layers are embedded with adjusted fine-tuned network hyperparameters to enhance forecasting accuracy. The results attain 0.379816, 0.616292, and 0.414586 for Mean Square Error (MSE), Root MSE, and Mean Absolute Error, respectively, providing significant insights into earthquake prediction. In addition, predicted seismic occurrences are plotted on a map to display their geographic location within the specified research region. This research provides significant value in facilitating the efficient distribution of resources, such as evacuating residents impacted by earthquakes or reinforcing buildings and infrastructure, for emergency responders and policymakers.


Fig. 1. Data collection scheme.
Fig. 2. Organization of IndoWaveSentiment files [ 1 ].
Fig. 3. Recording situation.
Fig. 4. Data annotating.
Data of actors.
IndoWaveSentiment: Indonesian Audio Dataset for Emotion Classification
  • Article
  • Full-text available

November 2024

·

10 Reads

Data in Brief

Voice is a one of media for human communication and interaction. Emotions conveyed through voice, such as laughter or tears, can communicate messages more quickly than spoken or written language. In sentiment analysis, the emotional component is crucial for reflecting human perceptions and opinions. This paper introduces IndoWaveSentiment, a dataset of emotional voice recordings categorized into five classes: neutral, happy, surprised, disgusted, and disappointed. The data collection took place in a recording studio with ten actors, evenly split between men and women. Each actor repeated the same sentence in Bahasa Indonesia three times for each emotion class, and the recordings were saved in .wav format. The annotation process was manually conducted using Audacity and validated through a questionnaire-based sampling technique that supports audio data. This dataset is valuable for researchers in Signal Processing and Artificial Intelligence, aiding the development of classification models within Machine Learning.

Download


Figure 3. Login Page
Figure 4. Dashboard Page
Questionnaire results
Respondent score Number of respondent scores SS 23 x 5 155
WebGIS-Based Land Asset Visualization (Case Study: Pangkep Regency Government)

August 2024

·

16 Reads

International Journal of Informatics Economics Management and Science

This study discusses the implementation of e-Government in Pangkep Regency with the aim of improving public services, especially in land asset management. This research responds to requests from the Department of Housing, Settlement Areas and Land (Disperkimtan) by addressing the challenges of complex administrative procedures and increasing public awareness of land asset management. The goal is to design a web-based Land Asset Mapping Information System using WebGIS to simplify administrative processes and increase transparency. This research applies the Rapid Application Development (RAD) method. The results show an effective user interface (UI) in land certificate creation as well as smooth functions in the login and land acquisition process. This system is able to handle user loads well, which is reflected in the user satisfaction rate of 76.4%.



Sistem Pendukung Keputusan: Konsep, Metode, dan Praktik

February 2024

·

365 Reads

Sistem Pendukung Keputusan (SPK) atau Decision Support System (DSS) adalah sistem informasi interaktif yang dirancang untuk membantu pembuat keputusan dalam menggunakan data dan model untuk memecahkan masalah yang tidak terstruktur atau semi-terstruktur. SPK menggabungkan sumber daya manusia dan komputer untuk menyediakan analisis data, peramalan, dan dukungan dalam pengambilan keputusan. Sistem ini sangat berguna dalam kondisi di mana keputusan tidak dapat dibuat secara otomatis, membutuhkan penilaian manusia, pengetahuan, dan keahlian. Buku ini membahas : Bab 1 Konsep Sistem Pendukung Keputusan Bab 2 Jenis Dan Proses Pengambilan Keputusan Bab 3 Metode Fuzzy Logic Bab 4 Metode Neural Network Bab 5 Metode Machine Learning Bab 6 Metode Deep Learning Bab 7 Metode Simple Additive Weighting (SAW) Bab 8 Analytical Hierarchy Process (AHP) Bab 9 Metode Technique For Order Preference By Similarity To Ideal Solution (Topsis) Bab 10 Metode Simple Multi Attribute Rating Technique (Smart) Bab 11 Metode Gray Absolute Decesion Analysis (GADA)


WebGIS Visualization of Infectious Disease Clustering with a Hybrid Sequential Approach

October 2023

·

51 Reads

·

1 Citation

Communications in Computer and Information Science

Infectious diseases are diseases that can be transmitted through various media. Based on the results of research that has been conducted at several Health Center in Gowa Regency, it is found that from 2020 to 2022, Health Center of Bontomarannu is one of the Health Center in Gowa Regency that handles many cases of infectious diseases, namely 212 cases of tuberculosis, 224 cases of dengue fever, and 427 cases of typhoid fever. This makes it difficult for the Health Center to classify what factors cause the increase in these diseases every day for one reason, namely the limitations of medical personnel to manually detect the indicators that cause the emergence of these diseases through medical record data. Based on data obtained through questionnaires given to patients of the Bontomarannu Health Center, there are several variables associated with infectious diseases. Therefore, this study aims to visualize the results of clustering infectious disease data (tuberculosis, dengue fever, and typhoid) per village in Gowa Regency in the form of WebGIS. The method used is K-means clustering which will be optimized using the Particle Swarm Optimization (PSO) algorithm to obtain better results. Moreover in the WebGIS visualization section, the frontend will be made using NextJS, the backend using Flask Py-thon, and for DBMS using SQLAlchemy. This WebGIS visualization will display cluster information for each village in Gowa Regency. Through quantitative analysis and clustering, the study aims to visualize the data and identify patterns and trends associated with infectious diseases in Gowa Regency, ultimately aiding in better decision-making and resource allocation for disease prevention and control.


INTEGRASI NATURAL LANGUAGE PROCESSING DALAM CHATBOT MARKETING (STUDI KASUS TOKO CAHAYA FAJAR)

August 2023

·

5 Reads

JURNAL INSTEK (INFORMATIKA SAINS DAN TEKNOLOGI)

Penelitian ini bertujuan untuk merancang aplikasi penjualan perlengkapan pernikahan dengan fitur chatbot dengan penerapan TF-IDF dan cosine similarity untuk meningkatkan akurasi sistem pendeteksi tanya jawab pada chatbot. Data ini diperoleh melalui observasi dan wawancara. Metode pengujian sistem menggunakan blackbox dan metode Frequency-Inverse Document Frequency (F-IDF). Hasil penelitian menunjukkan bahwa aplikasi untuk alat penjualan perlengkapan pernikahan dengan fitur chatbot menggunakan metode TF-IDF dan cosine similarity menampilkan hasil nilai dengan akurasi yang baik. Pengujian sistem menggunakan blackbox serta pengujian penerapan chatbot menggunakan pengujian validasi pada menggunakan recall dan precision menghasilkan nilai 90% dari hasil metode TF-IDF dan cosine similarity untuk akurasi tanya jawab chatbot.


Prediksi Tingkat Kejahatan dengan Metode Long Short Term Memory (Studi Kasus: Kota Makassar)

June 2023

·

66 Reads

Jurnal Minfo Polgan

Kota Makassar sebagai pusat dari Provinsi Sulawesi Selatan merupakan surga bagi para pelaku kejahatan. Hal ini berdasarkan tingginya kasus kriminalitas yang terjadi di kota Makassar. Berdasarkan data Kepolisian Resor Kota Besar Makassar angka kriminalitas yang terjadi di Kota Makassar pada tahun 2018 tercatat sebanyak 997 kasus. Angka tersebut menempatkan Makassar peringkat pertama tingkat kriminalitas dibandingkan daerah lainnya di Sulawesi Selatan. Dalam melakukan prediksi digunakan algoritma Long Short Term memory. Adapun parameter yang digunakan yaitu jumlah hidden layer, unit, epoch, batch size, dan learning rate. Didapatkan fungsi pelatihan dengan parameter Unit=64, Epoch=200, Batch size =16, Learning rate =0,001 dengan nilai RMSE 4,74. Dari hasil penelitian lokasi yang memiliki tingkat kriminal tertinggi terdapat pada kecamatan ujung pandang dengan jenis kejahatan yang paling sering terjadi yaitu penganiaayaan.


Unstructured road detection segmentation for autonomous car

November 2022

·

33 Reads

·

2 Citations

AIP Conference Proceedings

One of the important things in Autonomous Car technology is detecting the road so that it remains on the right lane, therefore this paper aims to be able to detect unstructured roads based on the results of the HSY color space segmentation on the road then produce vehicle position information from the center of the lane (center offset). In marking the roadside boundary, the method used is the Hough transform based on the resulting edge lines using an edge detector, then the coordinates of the left and right curb lines which represent the width of the road. The results of this paper indicate that the system’s ability to distinguish road and non-road areas on several roads with an average percentage of 99.59% for accuracy, 99.49% for precision and 98.84% for recall and the system’s ability to mark areas. The average road reaches 99.27% and the percentage error and accuracy obtained provide information on the position of the car from the center (center offset) based on the actual value and prediction results of 16.05% and 84.14%.


Citations (3)


... This phenomenon affects the community, where rainfall patterns are not decisive, showing the need for an effective and long-term strategy. With frequently recurring flood patterns and current climate change projections, the future of food security depends on productivity and the availability of food reserves, as well as efforts to overcome the challenges posed by climate risks such as flooding [10][11][12]. ...

Reference:

Evaluation of Rainwater Harvesting and Bio-pore Infiltration Holes for Flood Mitigation and Soil Conservation
Design of Flood Early Detection Based on the Internet of Things and Decision Support System

Ingénierie des systèmes d information

... In instances where the road edge detection is imprecise, the resultant navigation line quality suffers. Zainuddin, Suradi, and Warni refined this approach to mitigate the issues [27]. They implemented edge smoothing to diminish the irregularities of the edges, consequently augmenting the precision of the navigation centerline detection. ...

Unstructured road detection segmentation for autonomous car
  • Citing Conference Paper
  • November 2022

AIP Conference Proceedings

... Chen et al. [55] tested their approach using YOLO V3 in real-world conditions, achieving an accuracy of 85% in object detection and distance estimation. Indrabayu et al. [56] implemented the HOG + SVM method to detect motorcycles and modified motorcycles, reaching an accuracy of 89.70% for motorcycles and 95.16% for modified motorcycles. Song et al. [57] utilized YOLO V3 to enhance the detection accuracy of small vehicles, achieving an accuracy of 87.88%. ...

A Solution for Automatic Counting and Differentiate Motorcycles and Modified Motorcycles in Remote Area
  • Citing Article
  • January 2022

International Journal of Advanced Computer Science and Applications