Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal Foristek BERNAS: Jurnal Pengabdian Kepada Masyarakat Jurnal Ilmiah Intech : Information Technology Journal of UMUS Jurnal Algoritma Eduvest - Journal of Universal Studies
Dessy Santi
Jurusan Teknologi Informasi, Fakultas Teknik, Universitas Tadulako, Palu
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Education Electrical & Electronics Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Mathematics Neuroscience Nursing Public Health Social Sciences Veterinary Other

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Implementasi Naïve bayes Clasifier dalam Klasifikasi Jenis Berita Dessy Santi; Jumadil Nangi; Natalis Ransi
Foristek Vol. 10 No. 1 (2020): Foristek
Publisher : Foristek

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (362.383 KB) | DOI: 10.54757/fs.v10i1.52

Abstract

Sometimes the classification of news categories is still an obstacle. Classification can be wrong because it is still subjective. As a result, the selected category does not match the uploaded news description. Based on these problems, the authors feel the need to make Classification of News Types with the Naïve Bayes Classifier Algorithm. The importance of this system is to be able to classify news and help news seekers to get the news they want. Based on the test results, the Naïve Bayes Classifier algorithm has a good performance for the classification of news types. This is evidenced in testing using news data taken from www.kompasiana.com, then news is classified into four categories namely politics, economics, sports, and entertainment. The classification results using 16 test news obtained an accuracy of 87.5%.
Sistem Informasi Pengarsipan Surat-Surat Pada PT Sinergi Perkebunan Nusantara Dessy Santi; Meri Kristina Tongkuru
Jurnal Teknik Informatika UMUS Vol 2 No 01 (2020): Mei
Publisher : Universitas Muhadi Setiabudi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (808.206 KB) | DOI: 10.46772/intech.v2i01.186

Abstract

Pengelolaan surat dalam suatu organisasi memegang peranan penting dalam proses administrasi. Dalam hal ini sistem tata persuratan menjadi salah satu faktor yang berpengaruh dalam pengelolaan surat. Pada PT. Sinergi Perkebunan Nusantara,Pengelolaan surat masuk dan surat keluar dilakukan secara manual mulai dari pencatatan surat, proses pencarian, dan penyimpanan yang membutuhkan waktu dan biaya yang tidak efektif dan efisien. Sistem informasi pengarsipan adalah solusi dari permasalahan ini. Sistem informasi Pengarsipan ini juga memudahkan proses komunikasi data antar bagian. Sistem informasi ini dibuat dengan menggunakan PHP sebagai bahasa pemrograman , MySQL sebagai database dengan menngunakan Metode Rapid Application Development (RAD). Hasil dari penelitian ini adalah sebuah sistem informasi pengarsipan yang memberikan banyak kemudahan dalam proses pengelolaan surat surat termasuk pencarian surat, disposisi surat serta pendokumentasian dan pengarsipan surat-surat
CLUSTERING DAERAH TERDAMPAK SAMPAH DI INDONESIA MENGGUNAKAN ALGORITMA DBSCAN. Santi, Dessy; Maharani, Wulan; Syahrullah, Syahrullah; Nugraha, Deny Wiria; Mukhlis, Baso; Kali, Agustinus
Foristek Vol. 15 No. 1 (2025): Foristek
Publisher : Foristek

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54757/fs.v15i1.751

Abstract

The waste problem in Indonesia is a complex and evolving environmental issue, particularly in areas with high population density and economic activity. This study aims to cluster regions affected by waste issues using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. DBSCAN was chosen for its ability to identify spatial patterns and detect outliers without requiring a predefined number of clusters. The data used includes spatial and non-spatial information related to waste volume and regional characteristics across various provinces in Indonesia. The results show that DBSCAN effectively groups waste-affected areas into several clusters based on data density and spatial proximity. These clusters can serve as a foundation for determining policy priorities for regional and national waste management. This research is expected to contribute to the development of more targeted and data-driven waste management strategies.
Implementation of Long Short-Term Memory Algorithms on Cryptocurrency Price Prediction with High Accuracy on Volatile Assets Nursiana Zasqia, Andi Nirina; Laila, Rahmah; Trezandy Lapatta, Nouval; Yazdi Pusadan, Mohammad; Santi, Dessy; Wirdayanti
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2422

Abstract

Cryptocurrencies have emerged as one of the most popular digital assets, characterized by high volatility, which presents a significant challenge in forecasting their price movements accurately. This study aims to implement the Long Short-Term Memory (LSTM) algorithm to predict the prices of selected cryptocurrencies, including Bitcoin (BTC), Binance Coin (BNB), Ethereum (ETH), Dogecoin (DOGE), Solana (SOL), and Shiba Inu (SHIB). The LSTM model is trained using the Adam optimizer and employs early stopping to mitigate overfitting. Model performance is evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and the coefficient of determination (R²). The results indicate that the LSTM model achieves strong predictive accuracy for relatively low-volatility assets such as Dogecoin and Solana, with R² scores of 0.9795 and 0.9523, respectively. In contrast, its performance declines when applied to highly volatile assets like Bitcoin and Binance Coin. The findings also suggest that LSTM performs best in short-to-medium-term forecasts (7 to 30 days), but shows limitations in long-term predictions. This study contributes to the field by demonstrating the applicability of LSTM in financial forecasting and highlighting its strengths and constraints across different volatility profiles. Practically, the findings can assist traders and financial analysts in making data-driven decisions by applying LSTM models for more reliable short-term predictions, while emphasizing the need to integrate external market factors to enhance long-term forecast accuracy.
Pengenalan Dan Pelatihan Canva Sebagai Media Ajar Inovatif Bagi Guru Untuk Meningkatkan Mutu Pendidikan Di Smp Negeri 1 Lore Utara Wirdayanti; Santi, Dessy; Ardiansyah, Rizka; Laila, Rahma; Akbar, Muhammad; Syafa'at, Fizar
BERNAS: Jurnal Pengabdian Kepada Masyarakat Vol. 7 No. 2 (2026)
Publisher : Universitas Majalengka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31949/jb.v7i2.16763

Abstract

Program Pengenalan dan Pelatihan Canva sebagai Media Ajar Inovatif bagi guru di SMP Negeri 1 Lore Utaradilaksanakan untuk menjawab tantangan keterbatasan guru dalam mengembangkan media ajar digital yangkreatif dan interaktif, meskipun sebagian besar guru sudah memanfaatkan komputer dan internet sebatasmencari bahan ajar. Target utama program ini adalah meningkatkan literasi digital, keterampilan praktispembuatan media ajar berbasis Canva, motivasi guru dalam menggunakan teknologi pembelajaran, sertapeningkatan kualitas pengajaran melalui media digital yang menarik dan relevan dengan kurikulum. Capaianyang diraih meliputi peningkatan pemahaman guru tentang pemanfaatan teknologi, kemampuan membuatpresentasi, poster, infografis, hingga video pembelajaran sederhana, serta tumbuhnya kepercayaan diri guruuntuk mengintegrasikan Canva dalam proses belajar-mengajar. Metode pelaksanaan terdiri atas tigatahapan, yaitu: (1) tahap persiapan melalui survei awal (pre-test) yang menunjukkan mayoritas guru (74%)telah mengenal Canva sehingga pelatihan difokuskan pada pendalaman fitur; (2) tahap pelatihan denganmetode ceramah, diskusi, demonstrasi, praktik langsung, studi kasus, dan presentasi karya; serta (3) tahapevaluasi melalui post-test, pendampingan, dan supervisi implementasi di kelas. Hasil kegiatan menunjukkanbahwa guru sangat antusias, terbukti dari keterlibatan aktif selama pelatihan serta hasil survei akhir yangmenunjukkan 58% responden sangat puas dan 29% puas terhadap program. Pembahasan menunjukkanbahwa pelatihan ini efektif meningkatkan kompetensi digital guru, memotivasi penggunaan Canva secarakonsisten dalam pembelajaran, serta berdampak positif terhadap keterlibatan siswa di kelas. Dengandemikian, kegiatan ini berhasil mendorong peningkatan mutu pembelajaran melalui penguatan kompetensiTIK bagi guru di SMP Negeri 1 Lore Utara.
Analysis of the MTSN 2 Poso Education Data Collection System Using the Cognitive Walkthrough Method Rizaldi Agil Faturrahman; Amriana Amriana; Deny Wiria Nugraha; Rizka Ardiansyah; Dessy Santi
Eduvest - Journal of Universal Studies Vol. 6 No. 5 (2026): Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v6i5.52335

Abstract

This study examines the usability of the EMIS 4.0 website at MTsN 2 Poso using the Cognitive Walkthrough method. The increasing implementation of digital education management systems requires educational institutions to ensure that information systems are efficient, user-friendly, and capable of supporting accurate educational data management. However, several users of EMIS 4.0 still experience difficulties operating the system, particularly when completing administrative tasks. Therefore, this research aims to evaluate the usability level of EMIS 4.0 by identifying task completion success, user errors, efficiency, and user experience during system interaction. This study employed a quantitative usability evaluation approach using the Cognitive Walkthrough method. Data were collected from 20 teachers and education personnel selected through purposive sampling. Respondents were asked to complete seven task scenarios related to the use of EMIS 4.0. The results showed that the task completion rate reached 85%, while the error rate was 26%. Several tasks, such as updating employment data, uploading attendance documents, and printing portfolios, required longer completion times than other tasks. The time-based efficiency score obtained was 0.0272 goals/second. The findings indicate that EMIS 4.0 still requires improvements in interface design, feature accessibility, and server performance. In conclusion, the Cognitive Walkthrough method effectively identified usability problems and provided recommendations for improving the usability and user experience of the EMIS 4.0 system.
Co-Authors Agustinus Kali Amriana Amriana Baso Mukhlis Deny Wiria Nugraha Deny Wiria Nugraha Jumadil Nangi Laila, Rahma Maharani, Wulan Meri Kristina Tongkuru Mohammad Yazdi Pusadan Muhammad Akbar Natalis Ransi Nouval Trezandy Lapatta Nursiana Zasqia, Andi Nirina Rahmah Laila Rizaldi Agil Faturrahman Rizka Ardiansyah Rizka Ardiansyah Syafa'at, Fizar Syahrullah Syahrullah Wirdayanti