cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Risma Arta Juita ButarButar
Contact Email
risma.butarbutar@puterabatam.ac.id
Phone
628117777003
Journal Mail Official
comasiejournal.upb@gmail.com
Editorial Address
FAKULTAS TEKNIK DAN KOMPUTER UNIVERSITAS PUTERA BATAM (Sistem Informasi, Teknik Informatika & Teknik Industri) Jl. R. Soeprapto – Tembesi – Batam – Kepulauan Riau
Location
,
INDONESIA
Computer & Science Industrial Engineering Journal
Published by Universitas Putera Batam
ISSN : -     EISSN : 27156265     DOI : -
Core Subject : Science,
Computer Science & IT
Journal Comasie is a journal that combines 3 science namely informatics engineering, information systems and industrial engineering. The theme and scope can be seen in the scope section. This journal was created as a means of publicizing the results of research conducted by lecturers and students. This journal is published 3 times a year or every 4 months in a year. The main purpose of this journal is to facilitate students who want to publish their scientific work so that it will increase the profusion of knowledge. We on behalf of all the managers express gratitude for all efforts and support in the publication of this journal and our great hope that this journal can be a reference for the community in improving technology and to advance Indonesia (Amrizal, Andi, Welly, Rashid)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 839 Documents
 80   81   82   83   84 
IMPLEMENTASI DAN ANALISIS SENTIMEN PADA ULASAN APLIKASI GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA RoBERTa Nainggolan, Brian Natanael; Handoko, Koko
Computer Science and Industrial Engineering Vol 13 No 3 (2025): Comasie Vol 13 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i3.10501

Abstract

The rapid growth of Instagram user reviews on the Google Play Store poses challenges in understanding sentiment quickly and accurately. This research aims to develop an automatic sentiment analysis dashboard based on the Indonesian-RoBERTa model. Review data was collected using the google_play_scraper library and analyzed using a fine-tuned model. Fine-tuning was performed on the w11wo/indonesian-roberta-base-sentiment-classifier model using Indonesian tweet datasets during the PPKM period with 23,645 labeled data points (positive, neutral, negative). The preprocessing process included text cleaning, tokenization, and class weighting. Model evaluation used precision, recall, F1-score, and confusion matrix metrics. Test results showed good performance on positive and neutral classes, but performance on the negative class still needs improvement. The dashboard successfully performed scraping, sentiment prediction, and data visualization automatically. This research demonstrates the potential application of transformer-based models in Indonesian language and supports data-driven decision making.
PERANCANGAN APLIKASI PENDETEKSI STUNTING PADA BALITA DENGAN AUGMENTED REALTY Dofariando, Muhammad Ariel; Pangaribuan, Hotma
Computer Science and Industrial Engineering Vol 13 No 3 (2025): Comasie Vol 13 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i3.10519

Abstract

Stunting is a form of chronic malnutrition that causes impaired growth and development in children under five, especially in their first 1,000 days of life. The high prevalence of stunting in Indonesia, despite national reduction efforts, demands more effective and innovative early detection solutions. Conventional anthropometric measurements are still carried out manually and often overlooked by the public due to lack of awareness and tools. This research aims to design and implement an Android-based application utilizing Augmented Reality (AR) technology to assist in early detection of stunting in toddlers. The application uses the WHO Z-score Height-for-Age standard and camera-based real-time measurement with AR support on devices equipped with Time-of-Flight (ToF) sensors. The study applied a structured development methodology and was implemented using Unity and ARCore SDK. Users input the child’s age and weight, then scan the child’s height with their device, and the system automatically classifies stunting status visually and informatively. Testing showed that the application achieved an accuracy rate of approximately 99% at optimal lighting and scanning distance, with successful rendering of 2D and 3D objects. It also proved effective in raising awareness by offering educational content such as interactive visualizations, growth graphics, and parenting tips. The results confirm that the AR-based stunting detection application is functional, user-friendly, and informative, providing both a diagnostic tool and a medium for public health education. It supports government stunting reduction programs and empowers parents and healthcare workers in remote or underserved areas.
ANALISIS PENGENDALIAN KUALITAS PRODUK BATAKO DI UKM CETAK BATAKO SOBIRIN Alfajri, Muhammad; Aji Prasetyo, Bahariandi
Computer Science and Industrial Engineering Vol 13 No 3 (2025): Comasie Vol 13 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i3.10526

Abstract

The increase in the need for building materials must also be accompanied by an increase in the quality of these building materials. One of the building materialsthat is often used in building and housing construction is brick. The purpose of this stury is to determine the results of quality control of brick products using six sigma in reducing product defects in UKM Print Batako Sobirin. Quantitative results of DPMO and Sigma level calculations are carried out in each production year. Furthermore, the process DPMO is obtained in brick production year. Furthermore, the process DPMO is obtained in brik production with an average of 333333 defects. This means that the number of defects that may occur in every million units of poduct is 333333 units. The brick production process is at level 5, namely 1.934 sigma (in the category 233 defects – 233 defects – 6,210 defects). The process carried out still needs to be controlled and improved continuously in order to obtain a decreasing DPMO pattern ad a Sigma level pattern that increases over time to reach level 6 sigma. DMAIC imporvements are focused on the process starting with the preparation of the place, tools, and materials, followed by milling, molding drying, and testing the compressive strength of the bricks. Consequently,during the post-improvement phase (April-June 2025),the defect rate dropped to an average of 5,5%. Therefore,the application of DMAIC in the Sobirin Brick Making SME can be deemed successful in lowering product defect levels,though additional control is needed to reach optimal results.
AUGMENTED REALITY PENGENALAN ALAT-ALAT INSTALASI JARINGAN MENGGUNAKAN METODE MARKERLESS Firmansyah, Udhi; Annurrullah Fajrin, Alfannisa
Computer Science and Industrial Engineering Vol 13 No 3 (2025): Comasie Vol 13 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i3.10532

Abstract

Currently, technology is developing rapidly, making it easy to obtain information. Technology plays an important role in human life, offering many benefits in various fields and aspects of life, one of which is in the field of computer networks, where many network tools have been created with different functions and forms. Understanding network devices is crucial in education and training within the field of Information Technology. Now, a technology called AR (Augmented Reality) has emerged to simplify and provide innovative solutions that make learning more engaging and creative. The markerless method is employed so that the system can recognize the real environment without requiring markers or special tags, thereby offering greater flexibility in its application. This application was developed using Unity 3D with AR Foundation and ARCore as the primary technologies. 3D objects of network devices such as routers, MCI, LAN cables, and servers are displayed virtually in the real environment through the Android device's camera. Users can interact with the 3D objects, view descriptions of the device's functions, and play simple animations to clarify the device's usage. This research was conducted to design a Network Device Recognition application using a markerless method that makes it easier for salespeople or customers to understand the objects they want to see. The process is quite simple: just use a smartphone, and the application will scan the nearest flat surface to display the desired object, which will appear as a 3D object complete with information on its function, type, and price.
IMPLEMENTASI NEURAL NETWORK DENGAN METODE LSTM UNTUK PREDIKSI PENJUALAN CHINTARI CAKE AND COOKIES Suranti; Sunarsan Sitohang
Computer Science and Industrial Engineering Vol 13 No 3 (2025): Comasie Vol 13 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i3.10535

Abstract

In the competitive food and beverage industry sector, the ability to accurately predict demand is crucial to supporting effective production and marketing strategies. Chintari Cake and Cookies, a small and medium-sized enterprise (SME) specializing in homemade cakes and cookies, faces challenges in dealing with unpredictable demand fluctuations. This study aims to forecast daily sales using the Long Short-Term Memory (LSTM) algorithm, a type of Recurrent Neural Network (RNN) known for its effectiveness in processing sequential data and recognizing long-term patterns. LSTM was chosen due to its advantages over conventional statistical methods such as ARIMA, particularly in terms of prediction accuracy. Five years of historical sales data were used as model input, which was then processed through preprocessing stages before training the LSTM model. The prediction results were evaluated using RMSE (Root Mean Square Error) and MAPE (Mean Absolute Percentage Error) metrics. The results showed an RMSE value of 6.752 and a MAPE value of 6.792, indicating a low prediction error rate. These findings demonstrate that the LSTM algorithm can serve as an effective solution for SMEs in improving the accuracy of production planning and inventory management based on historical data patterns.
ANALISIS PERBAIKAN PROSES PRODUKSI TAHU PADA UKM TAHU BERKAH BAROKAH Sagita, Dandi; Fajrah, Nofriani
Computer Science and Industrial Engineering Vol 13 No 3 (2025): Comasie Vol 13 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i3.10548

Abstract

This study aims to analyze and propose improvements to the tofu production process at UKM Tahu Berkah Barokah based on Good Manufacturing Practice (GMP) and Workplace Improvement Strategies and Ergonomics (WISE) standards. Observations revealed several critical non-conformities, including an unclean and poorly maintained factory environment, inadequate sanitation facilities, and low employee awareness of personal hygiene. The average defect rate reached 14.98% per month, or 21,750 pieces out of 145,050 total production. The calculated DPMO value of 37,480 with a sigma level of 3.28 indicates inefficiencies in the process, while the Cpk value of 1.00 falls below the industry standard (≥1.33). Proposed improvements include enhancing workplace cleanliness, providing sanitation and OHS training, implementing production process supervision through documentation and regular audits, and encouraging active employee involvement in workplace innovation. The integration of GMP and WISE approaches is expected to reduce production defects, improve product quality, and create a healthier and more productive working environment on a sustainable basis.
ANALISIS PENINGKATAN KUALITAS PELAYANAN DAN PENANGANAN KELUHAN NASABAH PT BANK MANDIRI KCP BATM FANINDO Handoko, Prio; Aji Prasetyo, Bahariandi
Computer Science and Industrial Engineering Vol 13 No 4 (2025): Comasie Vol 13 No 4
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i4.10549

Abstract

silahkan berikan komentar anda
ANALISIS PENGENDALIAN KUALITAS PRODUKSI PADA PT TESE MANUFACTURING INDONESIA R Simanjuntak, Tommy Joshua; Aji Prasetyo, Bahariandi
Computer Science and Industrial Engineering Vol 13 No 4 (2025): Comasie Vol 13 No 4
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i4.10551

Abstract

This study aims to analyze and identify the causes of defective products in SENSOR - SSIC XCKN type lenses and propose quality control improvement efforts at PT TESE Manufacturing Indonesia. The main problem faced by the company is the high rate of rejected products exceeding the company's tolerance limit of 40%, with an average defect rate of 53.32% during the period of April 2024 to March 2025. Data show defect peaks in October 2024 (58,98%) and february 2025 (54,90%), which impact quality degradation, increased production costs, and potential losses. The method used in this research is Lean Six Sigma with the DMAIC (Define, Measure, Analyze, Improve, Control) approach. Through the Define phase, product defect issues are identified. The Measure phase is conducted to collect defect data and calculate the current DPMO (Defects Per Million Opportunities) and sigma level. In the Analyze phase, the root causes of defects will be identified using statistical tools such as Cause and Effect Diagrams and Pareto Charts. The Improve phase will formulate effective improvement solutions to reduce the defect rate. Finally, the Control phase will establish monitoring mechanisms to ensure the sustainability of improvements. After improvements were made, the product defect rate decreased to 38.69% of the established tolerance limit. It is expected that this research can provide concrete solutions to significantly reduce the number of defective products, improve production process efficiency, and help PT TESE Manufacturing Indonesia achieve better quality standards, moving towards a zero defect level and enhancing the company's competitivenes
ANALISIS PENGENDALIAN KUALITAS PIPA MARINE HOSE PADA PT YOKOHAMA INDUSTRIAL PRODUCTS MANUFACTURING INDONESIA Kurniawan, Nur Indra; Sumantika, Arsyad
Computer Science and Industrial Engineering Vol 13 No 4 (2025): Comasie Vol 13 No 4
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i4.10555

Abstract

This study explores the impact of integrating Failure Mode and Effect Analysis (FMEA) and Root Cause Analysis (RCA) on marine hose quality at PT Yokohama Industrial Products Manufacturing Indonesia. Driven by a defect rate that exceeded the 5% threshold (5.13% from June 2024 to May 2025), the research employed a descriptive quantitative design, using observation, documentation, and interviews. Among 937 defective units, surface cracks (468 cases, 39.8%), joint leaks (281 cases, 23.4%), and pipe deformations (188 cases, 15%) were most prevalent. FMEA assigned Risk Priority Numbers (RPNs), identifying cracking (RPN = 270), leakage (240), and deformation (144) as top risks. RCA with the 5 Whys revealed root causes: irregular vulcanization machine calibration, substandard raw materials, and inconsistent temperature control. Following corrective measures scheduled calibrations, raw material verification, and standardized vulcanization processes the defect rate dropped significantly. Over three months, defective units fell from 243 to 97 (a 40% reduction), and RPNs decreased: cracking to 120 (−55.6%), leakage to 90 (−62.5%), and deformation to 60 (−58.3%). These results confirm that combining FMEA and RCA effectively reduces failure risk, enhances product quality, and improves manufacturing efficiency.
SISTEM PENDUKUNG KEPUTUSAN DALAM MENENTUKAN JURUSAN DI SEKOLAH SMK NEGERI KOTA BATAM MENGGUNAKAN METODE SIMPLE ADDITIVE WEIGHTING Yusmet, Ramos; Dasa Putri, Anggia
Computer Science and Industrial Engineering Vol 13 No 3 (2025): Comasie Vol 13 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i3.10557

Abstract

The selection of academic majors at vocational high schools (SMK), particularly at SMK Negeri 7 Batam, often faces challenges in aligning students’ preferences with their academic capabilities. This issue arises due to the current New Student Admission Selection (SPMB) system, which allows students to select three program options, yet only the first choice is prioritized, resulting in frequent mismatches in placement when competition is high. To resolve this, a web-based Decision Support System (DSS) is developed using the Simple Additive Weighting (SAW) method to evaluate and recommend suitable majors based on academic performance and student interest. The system is built with Visual Studio Code as the development environment, Laravel as the PHP framework, and Unified Modeling Language (UML) to design system workflows and structures. The decision-making process involves score normalization, criteria weighting, and ranking of alternatives to produce optimal recommendations. Accessible through a web browser, the system supports students, teachers, and admission committees by providing a more efficient and accurate tool for academic major placement. Testing results demonstrate the system’s effectiveness in improving decision accuracy and supporting academic guidance processes within the vocational school environment.

Page 83 of 84 | Total Record : 839

 80   81   82   83   84 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol 13 No 4 (2025): Comasie Vol 13 No 4 Vol 13 No 3 (2025): Comasie Vol 13 No 3 Vol 13 No 2 (2025): Comasie Vol 13 No 2 Vol 13 No 1 (2025): Comasie Vol 13 No 1 Vol 12 No 4 (2025): Comasie Vol 12 No 4 Vol 12 No 3 (2025): Comasie Vol 12 No 3 Vol 12 No 2 (2025): Comasie Vol 12 No 2 Vol 12 No 1 (2025): Comasi Vol 12 No 1 Vol 11 No 4 (2024): Comasi Vol 11 No 4 Vol 11 No 3 (2024): Comasi Vol 11 No 3 Vol 11 No 2 (2024): Comasie Vol 11 No 2 Vol 11 No 1 (2024): Comasie Vol 10 No 5 (2024): Comasie Vol 10 No 4 (2024): Comasie Vol 10 No 3 (2024): Comasie Vol 10 No 2 (2024): Comasie Vol 10 No 1 (2024): Comasie Vol 9 No 8 (2023): Comasie Vol 9 No 7 (2023): Comasie Vol 9 No 6 (2023): Comasie Vol 9 No 5 (2023): Comasie Vol 9 No 4 (2023): Comasie Vol 9 No 3 (2023): Comasie Vol 9 No 2 (2023): Comasie Vol 9 No 1 (2023): Comasie Vol 8 No 4 (2023): Comasie Vol 8 No 3 (2023): Comasie Vol 8 No 2 (2023): Comasie Vol 8 No 1 (2023): Comasie Vol 7 No 7 (2022): Comasie Vol 7 No 6 (2022): Comasie Vol 7 No 5 (2022): Comasie Vol 7 No 4 (2022): Comasie Vol 7 No 3 (2022): Comasie Vol 7 No 2 (2022): Comasie Vol 7 No 1 (2022): Comasie Vol 6 No 5 (2022): Comasie Vol 6 No 4 (2022): Comasie Vol 6 No 3 (2022): Comasie Vol 6 No 2 (2022): Comasie Vol 6 No 1 (2022): Comasie Vol 5 No 7 (2021): Comasie Vol 5 No 6 (2021): Comasie Vol 5 No 5 (2021): Comasie Vol 5 No 4 (2021): Comasie Vol 5 No 3 (2021): Comasie Vol 5 No 2 (2021): Comasie Vol 5 No 1 (2021): Comasie Vol 4 No 6 (2021): Comasie Vol 4 No 5 (2021): Comasie Vol 4 No 4 (2021): Comasie Vol 4 No 3 (2021): Comasie Vol 4 No 2 (2021): Comasie Vol 4 No 1 (2021): Comasie Vol 3 No 5 (2020): comasie Vol 3 No 3 (2020): comasie Vol 3 No 2 (2020): comasie Vol 3 No 1 (2020): comasie Vol 1 No 01 (2019): Comasie Journal More Issue