Garuda - Garba Rujukan Digital

Rancang Bangun Fitur Chatbot Customer Service Menggunakan Dialogflow Jansen Wiratama; Samuel Ady Sanjaya; Victor Ilyas Sugara
Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika Vol 19, No 1 (2022): Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika
Publisher : Ilmu Komputer, FMIPA, Universitas Pakuan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33751/komputasi.v19i1.4474

The quality of providing customer service channels is very influential on customer satisfaction. To keep customer satisfaction, it is necessary to have a good interaction from customer service to the customer. In this case, PT Dian Prima Jayaraya is one of the companies that utilize Solo's application product as a medium for customer service. The development of the Solo application makes the application's features more complex and makes it difficult for users to do activities in the application. Customer service has a role in accommodating questions and answering difficulties experienced by users. The number of incoming questions is quite large, so that the existing customer service team cannot answer. Ignored or unanswered questions can lower the level of customer satisfaction. Therefore, we need a system that can help optimize customer service in a Chatbot to minimize unanswered customer questions. A chatbot is a service powered by rules and artificialintelligence, which the user interacts with through a chat interface. The Chatbot will be built on an iOS prototype application and use the NLP (Natural Language Processing) platform, namely Dialogflow. This platform will process and scan every question given by the customer.

Time-based Geospatial Analysis of Night-Time Light Data and Citizen Movement Restriction During Covid-19 Period Samuel Ady Sanjaya; Melissa Indah Fianty
G-Tech: Jurnal Teknologi Terapan Vol 7 No 2 (2023): G-Tech, Vol. 7 No. 2 April 2023
Publisher : Universitas Islam Raden Rahmat, Malang

Pembatasan kegiatan masyarakat atau di beberapa daerah disebut juga dengan lockdown sudah banyak dijalankan oleh beberapa negara demi menekan angka penyebaran Covid-19. Dalam penelitian ini, menggunakan foto satelit di malam hari, atau biasa disebut dengan Night Time Light (NTL) Data. Setelah itu diambil sample titik koordinat sebanyak 381 tempat umum di Jakarta dan diambil datanya menggunakan dataset VIIRS Stray Light Corrected Nighttime Day/Night Band Composites Version 1 selama kurun waktu Q1 2019 sampai dengan Q2 2022. Dari hasil foto satelit ini kemudian dikonversikan ke dalam bentuk numerik, dikorelasikan dengan timeline pembatasan kegiatan masyarakat di Indonesia dan juga data mobility untuk wilayah Jakarta. Hasilnya adalah ditemukan penurunan intensitas cahaya saat memasuki masa pembatasan kegiatann masyarakat sebanyak 1% - 16% di berbagai sektor. Penurunan intensitas ini tidak berkorelasi dengan kuat dengan data mobility untuk beberapa sektor yang menunjukkan perubahan penurunan aktivitas hingga 60%.

Machine Learning Approach of Obesity Level Classification: A Systematic Literature Review of Methods and Factors Steven Marcelino Tandiono; Samuel Ady Sanjaya
G-Tech: Jurnal Teknologi Terapan Vol 8 No 1 (2024): G-Tech, Vol. 8 No. 1 Januari 2024
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33379/gtech.v8i1.3604

The high prevalence of obesity over the years has become a global concern, as obesity contributes to an increased risk of many deadly diseases, such as diabetes, heart disease, and some cancers. This condition has become a serious concern for public health authorities, researchers, and the general public. Therefore, a comprehensive and effective approach is needed to tackle this obesity problem. Machine learning can be the answer to the required approach as it offers a method to predict the risk level of obesity through identifying the risk causes quickly and accurately. Through this approach, the most influential factors in obesity risk can be identified to aid in the development of more effective prevention and intervention strategies. Understanding the correlation between risk factors and obesity will hopefully lead to better solutions in addressing global obesity.

Utilization of Online Village Administration Services: Training on the use of Cihuni Village Website Features Jansen Wiratama; Rudi Sutomo; Raymond Sunardi Oetama; Samuel Ady Sanjaya; Santo Fernandi Wijaya
I-Com: Indonesian Community Journal Vol 3 No 4 (2023): I-Com: Indonesian Community Journal (Desember 2023)
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33379/icom.v3i4.3486

Public administration services are important for urban and rural communities. With a large population, it is difficult for administrative service processes using conventional methods to run optimally, so they need to be transformed into digital form. Current technology should support optimizing administrative services from village officers to the community. However, limitations related to the use of technology still need to be solved by village officers. Therefore, training is needed for village officers in using administrative service features via the Cihuni village website resulting from previous research. This training activity was carried out in Cihuni Village, a village supported by Multimedia Nusantara University (UMN). The training process involved the UMN Lecturer Team as community outreach members and Cihuni Village officers. This community outreach activity increases the understanding of village officials regarding using the Cihuni village website, which has various features for public administration services.

Perancangan Dasbor Pra-Bencana Tsunami di Gugus Mitigasi Lebak Selatan: Visualisasi dan Mitigasi di Panggarangan Richard Faustine Wong; Samuel Ady Sanjaya; Christopher Darren; Howard Yahya; Muhammad Fikri Riyadi
G-Tech: Jurnal Teknologi Terapan Vol 8 No 4 (2024): G-Tech, Vol. 8 No. 4 Oktober 2024
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/gtech.v8i4.4763

Tsunami telah meninggalkan tragedi di Indonesia, salah satunya tsunami Selat Sunda pada Lampung dan Banten. Diperlukan mitigasi bencana, tetapi kurangnya sinergi Badan Meteorologi, Klimatologi, dan Geofisika (BMKG) dengan pelaporan erupsi Pusat Volkanologi dan Mitigasi Bencana Geologi (PVMBG) menghambat upaya mitigasi dampak tsunami Selat Sunda. Untuk meningkatkan sinergi, dirancang dasbor pra-bencana tsunami dengan tujuan memaksimalkan pengurangan risiko bencana (PRB) di Panggarangan, Lebak. Perancangan dilakukan dengan metodologi Prototype, yang dilakukan secara sistematis mulai dari analisis kebutuhan GMLS, perancangan dengan menggunakan business intelligence tool bernama Tableau, pengujian dengan kuesioner System Usability Scale, kemudian revisi hingga dasbor sesuai kebutuhan. Harapannya, rancangan dasbor dapat meningkatkan sinergi antar-stakeholders, terutama di Panggarangan, serta mendukung pengambilan keputusan baik pihak yang berkepentingan dalam perencanaan tata kota maupun mitigasi bencana.

A Web-based Point of Sales for Automotive Component Industry using Rapid Application Development model Melvin Melvin; Jansen Wiratama; Rudi Sutomo; Samuel Ady Sanjaya
JOINS (Journal of Information System) Vol 8 No 2 (2023): Edisi November 2023
Publisher : Fakultas Ilmu Komputer, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/joins.v8i2.9383

This research aims to increase efficiency in Micro, Small, and Medium Enterprises (MSMEs) in the automotive components industry, focusing on CV Bengkel Megamakmur. This workshop is one of the MSMEs engaged in Indonesia's car spare parts industry. In the ongoing business process, these MSMEs need some help in inventory management, stock of goods, and less integrated sales transaction recording. The main problem identified was the discrepancy between the number of products sold and sales transaction reports. A web-based Point of Sale (POS) application was implemented, which allows the integration of inventory data and sales transactions. The method used in this research is Rapid Application Development (RAD), suitable for projects with limited resources and short work schedules. This research results in a Point of Sale application that can optimize business processes for managing inventory by monitoring stock and recording sales transactions in an integrated manner. This application has been tested using the System Usability Scale (SUS) method and obtained an average score of 86.6, included in the "very good" category. The test results show that this application has good functionality and can optimize MSME business processes in the automotive components industry.

Intelligent LSTM-based deforestation prediction model and dashboard for Kalimantan using global forest change and night-time light data Jansen Wiratama; Samuel Ady Sanjaya; Thomas Januardy; Reyhan Arya Hermawan; Santo Fernandi Wijaya
Jurnal Ilmu Komputer dan Sistem Informasi |JIKSI| Vol. 7 No. 2 (2026): Jurnal Ilmu Komputer dan Sistem Informasi (JIKSI) [in Progress]
Publisher : Institute of Information Technology and Social Science (IITSS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61346/jiksi.v7i2.333

Forest assessment based on predictions and evidence is an appropriate step toward environmental conservation. This study developed a Long Short-Term Memory (LSTM) based prediction model to monitor and predict forest cover and light intensity in Kalimantan. Using Global Forest Change (GFC) and Night-Time Light data, the prediction results are applied to a web-based dashboard. The data were available for the period from 2001 to 2023 and has been processed and aggregated to the provincial level. The LSTM model was trained using five optimizers, namely Adam, RMSprop, Stochastic Gradient Descent (SGD), Adadelta, and Adamax. Model performance was evaluated using Root Mean Squared Error (RMSE). The results showed that the Adam and RMSprop optimizers produced lower RMSE values compared to the other optimizers on the GFC dataset, making them more effective at learning patterns and forest cover change. On the NTL dataset, Adam, RMSprop, and Adamax demonstrated relatively similar performance due to the data’s more stable characteristics. Overall, Adam provided the most accurate and consistent predictions. The prediction results are presented via a web-based dashboard that allows for the visualization of historical trends as well as predictions of change in forest cover and nighttime light intensity. These findings suggest that the combination of the LSTM model and an interactive dashboard can support more effective deforestation monitoring.

Fuzzy Expert System for Melamine Moulding Compound Dye Feasibility Identification: A Case study on Plastic Industry Jansen Wiratama; Santo Fernandi Wijaya; Samuel Ady Sanjaya; Florentina Kurniasari; Hendro Budiyanto; Ala Al Kafri; Nuttaphat Sukchitt
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1498

This study addresses a practical decision problem within the melamine industry. Production managers are tasked with determining whether a new Melamine Moulding Compound (MMC) dye is suitable for use, based on testing parameters such as boiling point, processing time, and pressure. Given that these values frequently fall between established expert categories, manual decision-making can be challenging to justify and replicate. Accordingly, this research develops a web-based Fuzzy Sugeno expert system to assess the feasibility of MMC dye. The model incorporates three input variables, each characterized by low, medium, and high fuzzy sets. Expert knowledge is formalized into 27 rules employing zero-order Sugeno consequents for three classes: not feasible, conditionally feasible, and feasible. The system has been implemented as a PHP and MySQL application and is accessible via a publicly available login page. An illustrative example involving MMC103—boiling point of 165 °C, processing time of 65 seconds, and pressure of 55 bar—indicated medium and high membership values across all three parameters, activating eight rules. The aggregate firing strength was calculated as 3.00, the weighted consequent sum amounted to 80.00, and the final Sugeno score was 26.67. This score categorizes MMC103 as feasible. The results demonstrate that the model not only provides a classification label but also displays memberships, active rules, rule consequents, and the final computation, thereby enabling verification by the production manager. Furthermore, the study includes an English version of the application interface with privacy masking features for user data.

Fuzzy Expert System for Melamine Moulding Compound Dye Feasibility Identification: A Case study on Plastic Industry Jansen Wiratama; Santo Fernandi Wijaya; Samuel Ady Sanjaya; Florentina Kurniasari; Hendro Budiyanto; Ala Al Kafri; Nuttaphat Sukchitt
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1498

This study develops and evaluates an explainable zero order Fuzzy Sugeno expert system for assessing the feasibility of Melamine Moulding Compound (MMC) dyes in the melamine industry. The objective is to support consistent dye assessment by converting expert knowledge of boiling point, processing time, and injection pressure into a structured decision model. Each input variable is represented by low, medium, and high fuzzy sets, while four domain experts contributed to the definition and review of the membership ranges, rule base, and feasibility outcomes. The model contains 27 rules with singleton consequents of 10, 20, and 30 for not feasible, conditionally feasible, and feasible decisions, respectively, with midpoint decision boundaries of 15 and 25. The model was evaluated using 23 historical process profiles and classified 10 samples as not feasible (43.48%), 8 as conditionally feasible (34.78%), and 5 as feasible (21.74%). MMC103, with a boiling point of 165 °C, processing time of 65 seconds, and pressure of 55 bar, activated eight rules and produced a Sugeno score of 26.67, resulting in a feasible classification. A ±5% sensitivity analysis with 10,000 random perturbations produced MMC103 scores from 25.86 to 27.29 and retained its feasible classification in all runs, while overall class stability across the 23 profiles reached 98.86%. Sugeno classifications agreed with Mamdani inference for 20 of 23 profiles and with a crisp rule baseline for 18 profiles. By combining expert knowledge formalization, sensitivity evaluation, comparative analysis, and web implementation, this study provides an explainable and traceable decision support approach for MMC dye feasibility assessment in melamine production.

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search