Claim Missing Document
Check
Articles

Clustering Koridor Transjakarta Berdasarkan Jumlah Penumpang Dengan Algoritma K-Means Supriyatna, Adi; Carolina, Irmawati; Janti, Suhar; Haidir, Ali
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 4, No 2 (2020): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (978.801 KB) | DOI: 10.30645/j-sakti.v4i2.259

Abstract

Transportation is one of the facilities that make it easy for humans to carry out activities to move places using vehicles that are driven by humans or machines. Based on data obtained from data.jakarta.go.id, the number of Transjakarta bus passengers in corridors 1 to 13 of 2017 amounted to 114,239,960, and in 2018 there were 121,918,964 passengers. The algorithm used in this research is K-Means Cluster, which is implemented using Microsoft Excel and Rapidminer Studio. The purpose of this study is to cluster Transjakarta corridors based on the number of passengers divided into 3 clusters: high, medium, and low. The results of data processing show that the Transjakarta corridor data cluster is based on the number of passengers using the K-Means cluster algorithm using Microsoft Excel and Rapidminer Studio to produce 3 clusters, namely cluster 1 with the highest number of passengers, one corridor, cluster 2 with the number of passengers being nine corridors and cluster 3 or 0 with a low number of passengers there are three corridors. The highest number of passengers is corridor one which serves the Blok M - Kota route, indicating that the Blok M - Kota route is the most used by Transjakarta passengers.
Komparasi Algoritma Naive bayes dan SVM Untuk Memprediksi Keberhasilan Imunoterapi Pada Penyakit Kutil Supriyatna, Adi; Mustika, Wida Prima
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 2, No 2 (2018): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v2i2.78

Abstract

Warts is a skin health problem that is generally characterized by the appearance of small, rough-textured lumps on the skin surface caused by a virus that is human papilloma virus (HPV). One technique of treatment of wart disease is immunotherapy, this method is a treatment by boosting the immune system to overcome the disease of warts. Naive bayes and Support Vector Machine (SVM) is a method of data mining algorithm used to classify. The aim of this study was to compare the Naive bayes algorithm with Support Vector Machine (SVM) in predicting the success of immunotherapy treatment method in the treatment of wart disease. Tests conducted using the method of Naive bayes and Support Vector Machine (SVM) using the R programming language, then the results are used to do the comparison. The results of this study revealed that the Naive bayes method has superior prediction capability compared to Support Vector Machine (SVM) because Naive bayes can predict all class instances correctly with the accuracy level of 1.
Reinforcement learning for bitcoin trading: A comparative study of PPO and DQN Prasetyo, Romadhan Edy; Sumanto, Sumanto; Chaidir, Indra; Supriyatna, Adi
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.455

Abstract

Bitcoin’s high volatility demands automated strategies that adapt to changing market regimes while managing risk. This study compares Proximal Policy Optimization (PPO) and Deep Q-Network (DQN) for Bitcoin trading using hourly BTC/USDT data from 2019 to early 2025. The models are trained to generate buy and sell signals from technical indicators including the Relative Strength Index (RSI), MA20, volatility, Moving Average Convergence Divergence (MACD), volume trend, SMA200, and a weekly trend filter. All features are computed on hourly bars. The evaluation shows that PPO tends to trade more aggressively and delivers higher performance during bullish phases, though with greater risk in unstable markets. By contrast, DQN trades more selectively and maintains better stability in sideways or choppy conditions. These findings support the effectiveness of reinforcement learning for adaptive cryptocurrency trading and highlight complementary strengths between PPO and DQN across market regimes.
Penerapan Prototype Model Kampanye Indonesia Dermawan Pada Aksi Cepat Tanggap (Act) Janti, Suhar; Komarudin, Ishak; Supriyatna, Adi
Semnas Ristek (Seminar Nasional Riset dan Inovasi Teknologi) Vol 4, No 1 (2020): SEMNAS RISTEK 2020
Publisher : Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/semnasristek.v4i1.2466

Abstract

Teknologi ditambah kemanusiaan dapat menjadi sebuah keajaiban utuk menolong sesama manusia bahkan sesama mahluk hidup. Sejak tahun 2005 berdiri hingga kini organisasi Aksi Cepat Tanggap (ACT) selalu mengembangkan suatu solusi dalam bidang kemanusiaan. Indonesia Dermawan merupakan salah satu ide yang diusung di akhir tahun 2019 dengan bentuk kampanye kemanusiaan dapat membantu manusia lain yang membutuhkan dengan penyaluran donasi lebih cepat. Dengan adanya penelitian ini mempunyai tujuan menyediakan wadah berupa aplikasi web kampanye kemanusiaan yang dapat diajukan perorangan maupun kelompok yang ingin membuat kampanye untuk meminta pertolongan atau membantu orang lain. Model Prototype dipilih sebagai pendekatan atau metode yang dipakai untuk perancangan perangkat lunak dengan harapan dapat menghasilkan purwarupa yang memberikan penyamaan persepsi dan pemahaman akan proses dari aplikasi yang dirancang. Sehingga komunikasi yang baik akan tercipta antara pengembang dan pengguna sistem. Penelitian ini akan menghasilkan purwarupa dari aplikasi web Indonesia Dermawan yang diusung oleh ACT diakhir tahun 2019.