cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Herlambang Setiadi
Contact Email
h.setiadi@ftmm.unair.ac.id
Phone
+62881036000830
Journal Mail Official
jatm@ftmm.unair.ac.id
Editorial Address
Faculty of Advanced Technology and Multidiscipline, Gedung Kuliah Bersama, Kampus C Mulyorejo, Universitas Airlangga Jl. Dr. Ir. H. Soekarno, Surabaya, East Java 60115, Indonesia
Location
Kota surabaya,
Jawa timur
INDONESIA
Journal of Advanced Technology and Multidiscipline (JATM)
Published by Universitas Airlangga
ISSN : -     EISSN : 29646162     DOI : https://doi.org/10.20473/jatm.v1i2.40293
Core Subject : Science, Engineering,
Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Electrical & Electronics Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology
Journal of Advanced Technology and Multidiscipline (JATM) aims to explore global knowledge on sciences, information, and advanced technology. JATM provides a place for researchers, engineers, and scientists around the world to build research connections and collaborations as well as sharing knowledge on how addressing solutions to the (real world) problems through discoveries on cutting edge of science and technology. We encourage researchers to submit research in the following fields: ● Power System ● Control Systems ● Renewable Energy Technology ● Advanced Manufacturing ● Optimization & System Engineering ● Human Factors & Ergonomics ● Supply Chain & Logistic Management ● Waste Processing/ Waste Treatment ● Pollutant Removal ● Applied Chemistry ● Nano Medicine ● Sensor ● Artificial Intelligence ● Health Informatics ● Robotics & Mechatronics ● Computer Vision ● Data mining ● Human Computer Interaction ● Software Engineering ● Deep Learning ● Internet Of Things ● Natural Language Processing ● Learning Analytics & technologies ● Machine learning
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 43 Documents
 1   2   3   4   5 
A Comparative Study of Multinomial Naive Bayes and Long Short-Term Memory (LSTM) for Sentiment Classification on the IMDB Movie Review Dataset Yutika Amelia Effendi; Achmad Arif Mahzumi; Violeta Hawariznova Willes; Yahya Bachtiar Ivansyah
Journal of Advanced Technology and Multidiscipline Vol. 5 No. 1 (2026): Journal of Advanced Technology and Multidiscipline
Publisher : Faculty of Advanced Technology and Multidiscipline Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jatm.v5i1.85031

Abstract

This study presents a comparative analysis of two widely-used sentiment classification models—Multinomial Naive Bayes (MNB) and Long Short-Term Memory (LSTM)—using the IMDB movie review dataset. The research is centered on binary sentiment classification, identifying whether a movie review expresses a positive or negative sentiment. The preprocessing pipeline involves lowercasing, tokenization, removal of stopwords and special characters, and stemming (applied only in the LSTM pipeline). The MNB model employs a Bag-of-Words approach using CountVectorizer, while the LSTM model uses an embedding layer followed by a sequence-based deep learning architecture. Performance is evaluated using accuracy, precision, recall, and F1-score on a test set of 25,000 reviews. The Naive Bayes model achieved an accuracy of 85.93%, while the LSTM model outperformed it with an accuracy of 90%. Further tests on new, handcrafted reviews showed that the LSTM model exhibited higher confidence in predictions, especially in clearly polarized reviews. These findings highlight that while Naive Bayes is computationally efficient and performs adequately, LSTM offers superior accuracy and robustness in understanding semantic patterns in text. This research contributes to the development of more reliable AI-based sentiment analysis systems and offers insights for practitioners deciding between traditional machine learning and deep learning approaches in natural language processing tasks.
Characterization of the Performance of Electrospun Microfiltration Membranes with Variations in Support Layer and Processing Time Maulana Putra Kurniadi; Muslim Mahardika
Journal of Advanced Technology and Multidiscipline Vol. 5 No. 1 (2026): Journal of Advanced Technology and Multidiscipline
Publisher : Faculty of Advanced Technology and Multidiscipline Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jatm.v5i1.89904

Abstract

Microfiltration (MF) is a separation process that operates without phase change or mass transfer and is designed to retain particles in the micron size range, primarily for the removal of suspended solids from liquids. One of the promising fabrication methods for MF membranes is electrospinning, a technique capable of producing nanofibrous membranes using polymer solutions. To enhance membrane performance, modifications such as the incorporation of a support layer, forming a double-layer membrane, have been introduced to improve mechanical strength and filtration efficiency. This study was conducted through several stages, including membrane fabrication with variations in support layer type and electrospinning process time, followed by performance evaluation through Pure Water Flux (PWF) testing, UV-Vis spectrophotometry, contact angle measurements, and membrane morphology analysis. The membranes were fabricated using a polymer solution consisting of 18 wt% Polyvinylidene Fluoride (PVDF) dissolved in Dimethyl Sulfoxide (DMSO). The electrospinning process was carried out under controlled conditions with an applied voltage of 20 kV and a tip-to-collector distance (TCD) of 15 cm. The results showed that, in the support layer variation, the highest flux value was obtained with Support C at 12,501.40 L/h·m², while the lowest flux was observed with Support A at 7,577.79 L/h·m². In terms of rejection performance, Support B demonstrated the highest average rejection value of 89.29%, whereas Support C showed the lowest value of 48.25%. Based on these results, Support B was identified as the most suitable support layer due to its balanced performance in terms of permeability and rejection. Further investigation on process time variation revealed that the highest average rejection value of 88.91% was achieved at 60 minutes, while the lowest rejection of 74.72% occurred at 0 minutes. Contact angle measurements indicated that the highest average value of 125.33° was obtained at 45 minutes, and the lowest value of 104.67° was observed at 0 minutes. These findings indicate that increasing electrospinning time enhances membrane density and hydrophobicity, leading to improved filtration performance.
Development of an Ergonomic Reusable Face Mask using Additive Manufacturing: A Multidisciplinary Approach to Sustainable Respiratory Protectio Steven Abiel Yap; Muslim Mahardika
Journal of Advanced Technology and Multidiscipline Vol. 5 No. 1 (2026): Journal of Advanced Technology and Multidiscipline
Publisher : Faculty of Advanced Technology and Multidiscipline Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jatm.v5i1.90569

Abstract

The COVID-19 pandemic has necessitated global reliance on respiratory protection, leading to an unprecedented demand for face masks. This reliance has not only strained global supply chains but also triggered an environmental crisis characterized by a massive influx of non-biodegradable single-use medical waste. This research addresses these challenges by developing a reusable, ergonomic face mask that integrates systematic engineering design with additive manufacturing (3D printing) technologies. Using a multidisciplinary approach, we employed a design cycle comprising conceptual modeling, functional decomposition, and detailed parametric design, benchmarked against the NIOSH-approved 3M™ 6200 respirator. The prototype was fabricated via Fused Deposition Modeling (FDM), utilizing a composite material strategy: eTPU 95A for facial conformity and comfort, and PLA+ for the filter-locking mechanism to ensure structural rigidity. Advanced slicing strategies, specifically tree-like support structures, were employed to optimize surface finish and reduce post-processing requirements. The resulting prototype demonstrates the feasibility of bridging complex ergonomic requirements with rapid manufacturing capabilities. While further clinical validation and standardized filtration testing are required to achieve certified N95-level protection, this study establishes a scalable, sustainable, and customizable framework for the future of personal protective equipment (PPE) in public health management.

Page 5 of 5 | Total Record : 43

 1   2   3   4   5 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol. 5 No. 1 (2026): Journal of Advanced Technology and Multidiscipline Vol. 4 No. 2 (2025): Journal of Advanced Technology and Multidiscipline Vol. 4 No. 1 (2025): Journal of Advanced Technology and Multidiscipline Vol. 3 No. 2 (2024): Journal of Advanced Technology and Multidiscipline Vol. 3 No. 1 (2024): Journal of Advanced Technology and Multidiscipline Vol. 2 No. 2 (2023): Journal of Advanced Technology and Multidiscipline (JATM) Vol. 2 No. 1 (2023): Journal of Advanced Technology and Multidiscipline Vol. 1 No. 2 (2022): Journal of Advanced Technology and Multidiscipline Vol. 1 No. 1 (2022): Journal of Advanced Technology and Multidiscipline