cover
Contact Name
Mochamad Sulaiman
Contact Email
m.sulaiman@uniramalang.ac.id
Phone
+6282331527189
Journal Mail Official
m.sulaiman@uniramalang.ac.id
Editorial Address
Fakultas Sains dan Teknologi Universitas Islam Raden Rahmat Malang Jl. Raya Mojosari 02 Kepanjen-Malang
Location
Kota malang,
Jawa timur
INDONESIA
G-Tech : Jurnal Teknologi Terapan
ISSN : 25808737     EISSN : 2623064X     DOI : -
Jurnal G-Tech bertujuan untuk mempublikasikan hasil penelitian asli dan review hasil penelitian tentang teknologi dan terapan pada ruang lingkup keteknikan meliputi teknik mesin, teknik elektro, teknik informatika, sistem informasi, agroteknologi, dll.
Articles 897 Documents
Sentiment Analysis of Public Opinion on Deforestation in Papua on YouTube Platform Using Long Short-Term Memory (LSTM) Method Dolly Indra; Ramdaniah Ramdaniah; Nada Kayatri Ode
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.7855

Abstract

Deforestation in Papua has emerged as a significant environmental concern, attracting considerable attention due to its effects on biodiversity and the livelihoods of indigenous communities. This study seeks to examine public sentiment toward the issue by analyzing comments posted on the YouTube platform, employing the Long Short-Term Memory (LSTM) method. A dataset of 3,000 comments was gathered and processed through several stages, including text cleaning, tokenization, normalization, and Term Frequency–Inverse Document Frequency (TF-IDF) weighting. Subsequently, an LSTM model was developed and assessed using accuracy, precision, recall, and F1-score as evaluation metrics. The results reveal that the LSTM model achieved an accuracy of 88.43%, a precision of 90.01%, a recall of 97.49%, and an F1-score of 93.60%. Nevertheless, signs of overfitting were observed, indicated by lower validation performance compared to training results. These findings demonstrate that the LSTM approach is effective for identifying public opinion regarding deforestation and can serve as a valuable reference in decision-making and the formulation of environmental policies.
Tweet Sentiment Analysis with Support Vector Machine (SVM) Algorithm for PT. XYZ Digital Strategy Nazilatul Azza; Nur Hadian
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.7887

Abstract

The development of the digital era has encouraged the use of social media as a strategic tool for promotion and information dissemination, including in the publishing industry. PT. XYZ utilizes Twitter to raise awareness of literacy issues. This study analyzes public sentiment towards literacy through tweets with the hashtags #literasi, #literasiindonesia, and #penerbitbuku using the Support Vector Machine (SVM) algorithm. The research stages include scraping, preprocessing, labeling, TF-IDF vectorization, and evaluation with a confusion matrix. From the 466 tweets analyzed, a balanced distribution of positive and negative sentiments was obtained. The model produced an accuracy of 47.87%, precision of 47%, recall of 57%, and an F1-score of 51%. These results are lower than those of Afrillia et al. (2022), who achieved an accuracy of 70.8%, and Widyanto et al. (2023), who obtained 80.41% with an RBF kernel. These differences confirm the limitations of SVM on small datasets and informal language. This study contributes by showing the potential and limitations of SVM in analyzing literacy on social media. These results also emphasize the need for further research with larger datasets and advanced methods such as ensemble learning and deep learning (LSTM, BERT).
TikTok Live Chat Analysis Using NLP for Sales and Spam Detection: A Systematic Literature Review Setyaji, Wahyu Candra; Ratnasari, Novia; Widaningrum, Anisa Hudi; Septarina, Amalia Agung
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.7889

Abstract

The growing popularity of social commerce platforms such as TikTok Shop Live offers an interactive shopping experience through live streaming and chat features. However, many messages in the chat are irrelevant to sales, often containing spam or meaningless comments. This study examines the effectiveness of Natural Language Processing (NLP) methods in distinguishing between sales-related and spam chats to improve seller–consumer interactions. A systematic literature review was conducted on 13 articles focusing on spam detection and chat classification. The findings reveal that classical methods such as Naïve Bayes with TF-IDF achieve an accuracy of 85–90%, while K-Nearest Neighbor (KNN) and Logistic Regression are effective for simple cases with an accuracy of 80–87%. Deep learning methods deliver higher performance, with Long Short-Term Memory (LSTM) achieving 90–93% due to its strength in recognizing sequential patterns and informal language, while Convolutional Neural Networks (CNN) reach competitive accuracy rates of 88–91%. Transformer-based models, particularly Multilingual BERT, yield the highest accuracy (93–95%) because of their ability to capture contextual meanings in informal Indonesian texts. These findings confirm that a combination of classical and modern NLP methods is effective in supporting automated TikTok Live chat detection systems and can be further developed into real-time applications to enhance interaction quality, data-driven decision-making, and consumer satisfaction.
Design and Development of a Web-Based Tax Invoice Recapitulation Application Using the Optical Character Recognition (OCR) Method Zulfi Andriansah; Arip Kristiyanto
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.7930

Abstract

The process of recapitulating tax invoice data is crucial because it directly relates to a company's financial management. This process can be challenging for business owners when implemented using inefficient methods. For example, at CV Banten Inspirasi Mandiri, tax invoice data recapitulation is still carried out conventionally by manually entering data into Microsoft Excel. This approach is ineffective in terms of time efficiency and offers limited guarantees of data accuracy. To address this issue, an Artificial Intelligence (AI)-based application was developed to optimize the company's time and resources. Specifically, this system utilizes Optical Character Recognition (OCR) technology, which enables automatic data extraction from tax invoice files. The implementation results showed a time efficiency rate of 92.92%, with 100% accuracy for OCR results from PDF files and 89% for OCR results from JPG files, outperforming conventional methods, which only achieved 80% accuracy.
Implementation of Preventive Maintenance for CNC Machines in Vocational Education Facilities: A Case Study at Politeknik Kampar Romiyadi Romiyadi; Adi Febrianton
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.7951

Abstract

This research aims to optimize the preventive maintenance system for CNC machines in the context of vocational education, with a focus on improving practice efficiency and reducing downtime. The study was conducted at Politeknik Kampar using a quantitative-descriptive approach integrated with a case study method. Quantitative data were obtained from machine performance logs, including total operating hours, number of breakdowns, and maintenance time before and after preventive maintenance implementation. Descriptive data were gathered through structured interviews and direct observation of CNC training sessions. The research focused on two types of machines, namely the CNC Milling HURCO VM 10 and the CNC Turning Center SKT 160A, which are intensively used in practical training activities. Prior to the implementation of the preventive maintenance protocol, the existing maintenance system was reactive and unscheduled, leading to frequent breakdowns and extended operational downtime. Following the implementation of the preventive maintenance program over a six week period, the frequency of machine breakdowns decreased by approximately 45%, and average downtime was reduced from 6.2 hours to 3.4 hours per week. Consequently, practice efficiency increased by about 28%, as reflected in the higher completion rate of student machining tasks within the allocated schedule. Student involvement in daily maintenance also contributed to building practical awareness of the importance of maintenance in industrial settings. The findings demonstrate that preventive maintenance not only enhances machine reliability but also strengthens vocational learning processes based on hands-on skills.
Innovative Approaches to Post-Earthquake Reconstruction Material Evaluation for Healthy Simple Houses Junita Eka Susanti; Miskar Maini; Elian Zhafira
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.8007

Abstract

Post-earthquake housing reconstruction is essential for accelerating community recovery and ensuring safer living conditions in disaster-prone regions. This study evaluates the potential of recycled rubble sand from demolished masonry walls as an acceptable aggregate replacement in mortar production. It explores its integration into the development of a Healthy Simple House (HSH) model for post-disaster housing reconstruction. Laboratory experiments were conducted in accordance with PUBI-1982 and SII 0052-80 standards to characterize material properties and assess mechanical performance. The results indicate that rubble sand exhibits a well-graded particle distribution, stable density values (SSD 2.48 g/cm³, bulk 2.35 g/cm³, apparent 2.71 g/cm³), and moderate water absorption (5.62%), with slight organic contamination. Compressive strength tests showed that mortars with a 1:3 cement-to-sand ratio reached approximately 24 MPa at 28 days, meeting structural requirements, while higher rubble proportions reduced strength, restricting their application to non-structural components. The incorporation of rubble sand into the HSH model highlights its role in sustainable reconstruction by reducing reliance on natural resources while ensuring safe, healthy, and affordable housing. The study concludes that recycled rubble sand can be effectively utilized as a partial aggregate substitute, providing practical guidance for post-disaster housing programs and informing policy development for environmentally friendly and resilient reconstruction strategies that contribute to community resilience.
Numerical Analysis of Arc Geometry Variations on Bending Stability in Tied-Arch Bridges Izatullilah Izatullilah; Dzulkarnain Muhammad Khayzura; Faiz Razaan Nema; Dzul Fikri Muhammad
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.8030

Abstract

Tied-arch bridges are bridges that have high structural efficiency, but are prone to bending instability. This study aims to analyse the relationship between arc geometry variations and the bending stability of tied-arch bridges using the Finite Element Method (FEM) based on SAP2000 software, employing both linear and non-linear approaches. The linear analysis results show that lateral arch deformation occurs, indicating the potential for global lateral instability of the arch. Meanwhile, the non-linear analysis, which considers the significant geometry effect (P-Δ), produces a bending capacity of 7.43-11.69 kN with a maximum deflection of -0.52 mm. Variations in the arch angle were found to affect the critical bending capacity without significantly impacting global deformation. These findings are expected to serve as a valuable reference for designers and structural engineers in determining optimal and efficient arch designs.
Slope Stability Analysis of the Mahakam Monthly Pit Highwall Design at PT Arta Bumi Sakti Insani BaraPerkasa Site East Kalimantan Muhammad Faisal Siddiq; Yossa Yonathan Hutajulu; Ferdinandus Ferdinandus; Nuansa Mare Apui Ganang; Yusias Andri
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.8031

Abstract

PT Arta Bumi Sakti operates within the mining sector, focusing on the Insani Baraperkasa. A major challenge in open-pit mining in this area is maintaining the stability of highwall slopes, particularly in the 2025 Mahakam monthly pit design. This study aims to evaluate slope stability in the highwall region using the Limit Equilibrium Method through the Bishop Simplified, Janbu Simplified, Morgenstern Price, and Spencer. Geotechnical parameters were obtained from laboratory tests and interpretations of geotechnical drilling data, including unit weight, cohesion, internal friction angle, UCS, and GSI. Software was used to analyze the slope and calculate safety factors while considering groundwater levels, earthquake loads, and ground pressure across two representative cross-sections. The results show that both cross-sections have safety factor values exceeding the minimum threshold established by the Ministry of Energy and Mineral Resources Regulation No. 1827 K/30/MEM/2018, namely, FS > 1.1 and PoF < 20%. Thus, mining activities in this period can be conducted safely. In addition, the Spencer Method, which simultaneously satisfies stability in terms of force and momentum, provides stable results, this can be used as the basis that the Spencer can be used as the main method in the analysis of slope stability in the location.
Analysis of Potential Damage to Hydrotester Machines Using FMEA and FTA Methods at PT. ISP to Improve Maintenance Reliability Johan Wiranaka; Deny Andesta; Efta Dhartikasari
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.8044

Abstract

PT. Indal Steel Pipe (ISP) is a steel pipe manufacturing company that relies on hydrotester machines as an essential tool to ensure product quality. The high production volume and intensive use of machinery have led to frequent failures, such as water hose leakage, rubber seal damage, and electrical system failure. These issues led to unplanned downtime of up to 3.09% of total operating time and 400 minutes of repairs in the last six months, which reduced productivity. This study aims to identify the hydrotester components with the highest risk of failure and establish maintenance priorities. The methods applied are Failure Mode and Effect Analysis (FMEA) and Fault Tree Analysis (FTA). FMEA is used to calculate the Risk Priority Number (RPN) based on severity, frequency, and detection, while FTA helps to systematically trace the root cause of failure. The results showed that the broken pipe rubber had an RPN value of 245, followed by a leaky hydrolis with an RPN of 180, followed by a leaking water pipe hose with an RPN value of 168. Further FTA analysis identified material wear and excessive operational stress as the dominant causes of failure. These findings highlight that combining FMEA and FTA provides an effective approach in formulating maintenance strategies, thereby minimizing risk, reducing downtime, and ensuring production continuity. The novelty of this study lies in integrating FMEA and FTA to prioritize maintenance actions specifically for hydrotester machines, offering practical guidelines for industries with similar equipment.
Flow Resistance Estimation Using the Empirical Chezy Method in Sediment-Laden Flow Miskar Maini; Junita Eka Susanti
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.8057

Abstract

Hydraulic resistance, represented by the Chezy coefficient, is crucial in estimating flow discharge in open channels and serves as a fundamental parameter in designing hydraulic structures such as irrigation canals and river control facilities. This study investigates the behavior of the Chezy coefficient under non-sediment-laden (NSL) and sediment-laden (SL) flow conditions through controlled laboratory experiments using coarse sand, complemented by comparative analysis with data from irrigation channels and natural rivers. The results show that the ratio of mean velocity to shear velocity (U/u*) exhibits a robust correlation with discharge (Q) under both flow conditions, with a determination coefficient (R²) exceeding 0.96. The hydraulic radius (Rh) also shows a strong linear relationship with discharge (R ≈ 0.98), confirming its role in the empirical estimation of the Chezy coefficient (C). The value of C increases with higher velocity ratios but tends to be slightly lower under SL conditions due to increased resistance from suspended sediments. The Mean Absolute Error (MAE) value of 0.02 indicates a slight difference between NSL and SL conditions. These findings suggest that the empirical method is unreliable and exhibits significant differences in estimating Chezy under sediment-laden flow. It highlights the need for supplementary approaches to improve irrigation and river management design accuracy.