Garuda - Garba Rujukan Digital

Prediksi Kebakaran Hutan Berdasarkan Titik Panas dan Iklim Menggunakan Algoritma Random Forest Firmansyah, Aditya; Syahidin, Muhammad Farhan; Triana, Yaya Sudarya
Jurnal Nasional Teknologi dan Sistem Informasi Vol 10, No 2 (2024): Agustus 2024
Publisher : Jurusan Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v10i2.2024.145-155

Kebakaran hutan dan lahan semakin sering terjadi, menyebabkan dampak lingkungan yang menyebar ke luar wilayah kebakaran. Permasalahan yang terjadi salah satunya karena musim kemarau yang panjang di wilayah Kabupaten Ogan Komering Ilir Provinsi Sumatra Selatan yang menjadi faktor utama dalam meningkatnya risiko kebakaran, sebanyak 1.111 titik kebakaran tercatat pada tahun 2023. Permasalahan lainnya juga pada titik panas yang salah mendeteksi kebakaran yang seharusnya tidak kebakaran dan kasus tidak kebakaran yang seharusnya kebakaran, hal tersebut menyebabkan kerugian lingkungan maupun kerugian dana. Oleh karena itu, dibutuhkan model klasifikasi untuk memprediksi kasus kebakaran. Penelitian ini menggunakan gabungan data titik panas dan data iklim sebanyak 4343 data menggunakan metode Random Forest. Proses yang dilakukan yaitu studi literatur dan tahapan prediksi yang terdiri dari web scraping, data pre-processing, splitting data, pemodelan, dan evaluasi. Hasil penelitian berupa laporan klasifikasi, confusion matrix, dan feature importance. Hasil pengujian menunjukkan tingkat akurasi model yang baik sebesar 85.8% yang menunjukkan model menghitung seberapa tepat kinerja yang dilakukan model. Dengan penerapan model menggunakan metode Random Forest, model prediksi ini mengidentifikasi kasus kebakaran sangat baik sehingga informasi ini dapat digunakan untuk keputusan manajemen penanggulangan kebakaran dengan tepat dan meminimalisir terjadinya kerugian.

User behavior analysis for insider attack detection using a combination of memory prediction model and recursive feature elimination algorithm Triana, Yaya Sudarya; Osman, Mohd Azam; Stiawan, Deris; Budiarto, Rahmat
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i2.pp1793-1804

Existing defense tools against the insider attacks are rare, not in real time fashion and suffer from low detection accuracy as the attacks become more sophisticated. Thus, a detection tool with online learning ability and better accuracy is required urgently. This study proposes an insider attack detection model by leveraging entity behavior analysis technique based on a memory prediction model combined with the recursive feature elimination (RFE) feature selection algorithm. The memory-prediction model provides ability to perform online learning, while the RFE algorithm is deployed to reduce data dimensionality. Dataset for the experiment was created from a real network with 150 active users, and mixed with attacks data from publicly available dataset. The dataset is simulated on a testbed network environment consisting of a server configured to run 4 virtual servers and other two computers as traffic generator and detection tool. The experimental results show 94.01% of detection accuracy, 95.64% of precision, 99.28% of sensitivity, and 96.08% of F1-score. The proposed model is able to perform on-the-fly learning to address evolving nature of the attacks. Combining memory prediction models with the RFE for user behavior analysis is a promising approach, and achieving high accuracy is definitely a positive outcome.

DATA SCIENTIST CERTIFICATION GUIDANCE FOR SENIOR HIGH SCHOOL AND UNIVERSITY STUDENTS Triana, Yaya Sudarya; Budiarto, Rahmat; Rahmad, Khozaeni Bin
Jurnal Pengabdian Masyarakat Nasional Vol 5, No 1 (2025)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/pemanas.v5i1.30343

The importance of using Information and Communication Technology can increase our role in the Modern Era among academics, which is one of the driving factors to be able to compete in the digital world. The use of technology is not only for social media, but the use of technology has an important role in the world of work today. The increasingly rapid development of technology has created many changes and updates in every field. One of the applications most widely used and needed by society is Data Science. Data Science is a multi-disciplinary science that is very widely used in both exact and social fields. To make your job search easier, Data Scientist certification is required. This of course requires someone who is competent in their field. Today's young generations should be worthy of having these competencies. Based on the above, the lecturers at the Faculty of Computer Science, Universitas Mercu Buana contributed to providing a coaching understanding in the application of Information and Communication Technology to increase knowledge in the Modern Era among academics so that they can equip the younger generation to have certification in the field of information technology, especially Data Scientists. This activity or training is a form of concern and is also one of the duties as a lecturer at the Faculty of Computer Science who understands information technology, especially in the field of Data Science.

Entity-Relationship Diagram Technique in Database Palinggi, Owen Baan; Triana, Yaya Sudarya; Permana, Muhamad Bagas; Huda, Darul Fitahul; Priyono, Kus Andi
Journal Collabits Vol 2, No 2 (2025)
Publisher : Journal Collabits

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/collabits.v1i2.27252

The Entity Relationship Diagram (ERD) is one of the most important data modeling techniques in the database design process. ERDs are used to represent data in a conceptual form before being implemented into the actual database schema. By using an ERD, developers can illustrate the relationships between entities, the attributes possessed by each entity, and the types of relationships that occur between these entities.The use of ERDs in database design has several main benefits. First, ERDs help to accurately and consistently model data requirements before the implementation stage. Second, ERDs provide a clear visual representation of the data structure, facilitating communication and understanding among team members. Third, ERDs serve as the basis for designing an efficient and well-structured database schema.Despite being an essential technique, many developers still struggle with creating accurate and appropriate ERDs. Errors in designing ERDs can cause serious problems in database implementation, such as data redundancy, anomalies, or even data loss. Therefore, a deep understanding of the concepts and rules in creating ERDs is crucial.In this journal, an example of a correct ERD will be presented along with a detailed explanation of each entity, attribute, and relationship involved. This discussion is expected to provide guidance for readers in designing accurate ERDs that meet the requirements, thereby producing an efficient database.

Web-Based Brader Barbershop Service Application Sumantri, Bagas; Triana, Yaya Sudarya; Maesaroh, Siti
Journal Collabits Vol 2, No 1 (2025)
Publisher : Journal Collabits

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/collabits.v2i1.32710

The development of information technology has been widely implemented in various types of businesses, both businesses in the sale of products and businesses in the service sector, in order to facilitate the work process. The design of the barbershop service application aims to help manage the service process in the barbershop location area. Based on researchers' observational data, the condition of the barbershop which has many customers every day has service constraints in the queue of orders and payment transactions at the barbershop. This results in loss of customer time as well as from employees and barbershop owners. From this problem, we need a service application that is expected to minimize the density of customer queues in ordering services and payments. The analysis and design of this application aims to help the owner of the barbershop in serving customers, using structured system development (SDLC) modeling that has limits or scope of research that starts from the planning to the design stage, namely the application interface design. So this research can produce customer service application designs that can help solve customer queue service problems.

Prediksi Kebakaran Hutan Berdasarkan Titik Panas dan Iklim Menggunakan Algoritma Random Forest Firmansyah, Aditya; Syahidin, Muhammad Farhan; Triana, Yaya Sudarya
Jurnal Nasional Teknologi dan Sistem Informasi Vol 10 No 2 (2024): Agustus 2024
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v10i2.2024.145-155

Kebakaran hutan dan lahan semakin sering terjadi, menyebabkan dampak lingkungan yang menyebar ke luar wilayah kebakaran. Permasalahan yang terjadi salah satunya karena musim kemarau yang panjang di wilayah Kabupaten Ogan Komering Ilir Provinsi Sumatra Selatan yang menjadi faktor utama dalam meningkatnya risiko kebakaran, sebanyak 1.111 titik kebakaran tercatat pada tahun 2023. Permasalahan lainnya juga pada titik panas yang salah mendeteksi kebakaran yang seharusnya tidak kebakaran dan kasus tidak kebakaran yang seharusnya kebakaran, hal tersebut menyebabkan kerugian lingkungan maupun kerugian dana. Oleh karena itu, dibutuhkan model klasifikasi untuk memprediksi kasus kebakaran. Penelitian ini menggunakan gabungan data titik panas dan data iklim sebanyak 4343 data menggunakan metode Random Forest. Proses yang dilakukan yaitu studi literatur dan tahapan prediksi yang terdiri dari web scraping, data pre-processing, splitting data, pemodelan, dan evaluasi. Hasil penelitian berupa laporan klasifikasi, confusion matrix, dan feature importance. Hasil pengujian menunjukkan tingkat akurasi model yang baik sebesar 85.8% yang menunjukkan model menghitung seberapa tepat kinerja yang dilakukan model. Dengan penerapan model menggunakan metode Random Forest, model prediksi ini mengidentifikasi kasus kebakaran sangat baik sehingga informasi ini dapat digunakan untuk keputusan manajemen penanggulangan kebakaran dengan tepat dan meminimalisir terjadinya kerugian.

Title

Found 16 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 16 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 16 Documents
Search