Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Journal of Soft Computing Exploration Prosiding Seminar Nasional Biologi Scientific Journal of Informatics
Ryo Pambudi, Ryo
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

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

Found 3 Documents
Search

 1 
Analysis of public opinion sentiment against COVID-19 in Indonesia on twitter using the k-nearest neighbor algorithm and decision tree Pambudi, Ryo; Madani, Faiq
Journal of Soft Computing Exploration Vol. 3 No. 2 (2022): September 2022
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v3i2.88

Abstract

COVID-19 has become an ongoing disease pandemic across the globe. The need for information makes social media such as twitter a place to exchange information. This tweet can be used to see public sentiment towards COVID-19 in Indonesia. Sentiment analysis classifies opinions from tweets that have been processed and classified into different sentiments, namely negative, neutral, or positive. The aim of this paper is to find the algorithm that has the best accuracy. The researcher proposes to compare the K-Nearest Neighbors (KNN) and decision tree algorithms to be used in the classification of sentiment data from tweets related to COVID-19 that took place in Indonesia. The results of the evaluation of performance metrics concluded that the decision tree algorithm has a higher level of accuracy than KNN. Decision tree produces accuracy = 0.765, error = 0.235, recall = 0.76, and precision = 0.767 which is better when compared to KNN which produces accuracy = 0.69, error = 0.31, recall = 0.66, and precision = 0.702.
PENGEMBANGAN CHATBOT LAYANAN DAN INFORMASI LABORATORIUM FISIOLOGI TUMBUHAN FMIPA UNNES BERBASIS TELEGRAM Sriyadi, Sriyadi; Hadiyanti, Lutfia Nur; Suwarti, Suwarti; Pambudi, Ryo
Prosiding Seminar Nasional Biologi Vol. 13 (2025)
Publisher : Prosiding Seminar Nasional Biologi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Laboratorium merupakan tempat untuk melakukan kegiatan akademik berupa praktikum, penelitian dan pelatihan, serta dapat diberdayakan untuk melakukan aktivitas penunjang Tri Dharma Perguruan Tinggi. Laboratorium Fisiologi Tumbuhan FMIPA UNNES terus berupaya untuk memberi pelayanan yang terbaik. Permasalahan yang diungkapkan penelitian ini adalah belum tersedianya sistem informasi dan layanan laboratorium fisiologi tumbuhan secara online. Informasi dan layanan laboratorium sudah tersedia namun pengguna harus datang ke laboratorium apabila hendak mendapatkan informasi dan layanan laboratorium. hal ini tentu saja tidak sesuai dengan prinsip kecepatan dan kemudahan layanan laboratorium. Adapun tujuan dari penelitian ini adalah yang pertama perlunya menyusun informasi Laboratorium Fisiologi Tumbuhan secara sistematis, lengkap dan terbaru. Yang kedua merancang sistem informasi dan layanan laboratorium Fisiologi Tumbuhan yang dapat diakses dengan mudah dan cepat. Pada penelitian ini diusulkan sebuah solusi dengan mengembangkan Chatbot informasi dan layanan laboratorium berbasis telegram. Metode pengembangan yang digunakan untuk membangun perangkat lunak Chatbot menggunakan model waterfall. Pengembangan dimulai dengan, analisis kebutuhan, perancangan, implementasi (pemrograman), pengujian, dan perbaikan aplikasi. Hasil dari penelitian ini, berupa rancangan Chatbot berbasis Telegram. Chatbot menyediakan berbagai informasi dan layanan laboratorium sebanyak delapan kategori perintah atau menu sebagai prototype awal. Dari hasil pengujian yang telah dilakukan, perintah masing-masing kategori informasi dan layanan dapat berjalan dengan baik dan memberikan respon sesuai yang diharapkan. Chatbot dapat digunakan sebagai media informasi dan layanan laboratorium Fisiologi Tumbuhan FMIPA UNNES yang dapat diakses oleh pengguna dengan mudah dan cepat.
Comparative Performance Analysis of Deep Learning Models for Cryptocurrency Price Forecasting Pambudi, Ryo; Mutiara Kusumo Nugraheni, Dinar; Puji Widodo, Aris
Scientific Journal of Informatics Vol. 12 No. 4: November 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i4.35653

Abstract

Purpose: A cryptocurrency's high volatility and nonlinear market dynamics make it extremely difficult to predict its price with any degree of accuracy. This study aims to evaluate and contrast the predictive capabilities of five Deep Learning architectures for the same reason: LSTM, GRU, BiLSTM, Transformer, and Performer, to identify the best model capable of predicting the price of cryptocurrencies. It is aimed at providing an empirical base for making such predictions with high reliability in such volatile financial markets. Methods: The dataset used in this study, namely the price per minute data for BTC, ETH, BNB, and XRP, was obtained from Kaggle. Data processing includes normalization using MinMaxScaler and sequence generation through the Sliding Window technique. An 80:20 data split is used to train and validate each deep learning model, and four metrics consisting of MAE, MSE, RMSE, and MAPE are used for evaluation. Standardized experimental protocols were guaranteed by Python-based frameworks.  Result: The Transformer model created the best results for the lowest MAPE value across all datasets, the smallest being BTC and ETH at 0.20%, BNB at 0.29%, and XRP at 0.36% demonstrating high accuracy and generalization. The BiLSTM was ranking second since it captured effectively the bidirectional temporal dependencies; the GRU was moderate but stable in its performance. The data showed that the accuracy of LSTM and Performer varied. Novelty: This research provides a comprehensive comparison between various models, highlighting the Transformer's self-attention mechanism as the most superior in capturing long-term temporal dependencies and nonlinear market behavior compared to other deep learning methods. These findings provide valuable insights for the development of advanced AI-based forecasting frameworks in financial analysis.
Co-Authors Lutfia Nur Hadiyanti, Lutfia Nur Madani, Faiq Mutiara Kusumo Nugraheni, Dinar Puji Widodo, Aris Sriyadi Sriyadi, Sriyadi Suwarti Suwarti