cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
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
Published by Universitas Islam Raden Rahmat Malang
ISSN : 25808737     EISSN : 2623064X     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Decision Sciences, Operations Research & Management Energy Engineering
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.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 929 Documents
 89   90   91   92   93 
Evaluation of the Level of Physical Damage Due to Erosion in Post-Sand Mining Land Using the Universal Soil Loss Equation (USLE) Method Novalisae Novalisae; Noveriady Noveriady; I Putu Putrawiyanta; Ferdinandus Ferdinandus; Yulius Kahanjak; Grace Any Pasaribu
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9341

Abstract

Sand mining activities at Km. 29 in Bukit Batu District, Palangka Raya City, have caused significant physical land damage. This study quantifies erosion rates in former sand mining areas using the Universal Soil Loss Equation (USLE) through field surveys and laboratory analysis. Soil samples were collected purposively from four locations (Kolong 1 TL, Kolong 2 TL, Kolong 1 BD, Kolong 2 BD) at 0-20 cm depth with three replications. Results showed erosion rates ranging from 0.54 to 2.52 tons/ha/year, classified as “very low” according to standard erosion hazard categories. However, in post-mining contexts with initial degradation, these rates indicate serious land vulnerability. The dominant factors influencing erosion were high rainfall erosivity (R=998.45 MJ.mm/ha/hr/year), minimal vegetation cover (C=0.8), and the absence of conservation practices (P=1), whereas soil erodibility was inherently very low (K=0.005-0.014). Although numerically classified as very low, the former sand mining land requires immediate conservation intervention. Practical implications emphasize integrated conservation through vegetative approaches (fast-growing cover crops) and mechanical methods (gulud terraces and rorak), focusing on modifying the conservation practice factor (P) as the most easily intervenable variable to prevent increased erosion and restore land conditions.
Privacy-Focused AIoT: Implementing an Offline Voice Assistant for Smart Building Management Using Local LLMs Fitri Wibowo; Suheri Suheri; Ferry Faisal; Freska Rolansa
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9342

Abstract

Voice assistants are increasingly used for smart building control, yet cloud-based architectures raise privacy risks and become unavailable during internet outages. This study designs and evaluates a fully offline AIoT voice assistant for smart building management using local speech and language models. The system employs an edge audio node (Raspberry Pi Zero 2W with ReSpeaker 2-Mics Pi HAT) and a local GPU server running containerized microservices for speech-to-text (Whisper), intent understanding and action planning (Ollama-hosted LLMs), and text-to-speech (Piper). Building devices and sensors are integrated through Home Assistant, enabling voice-driven control and monitoring without sending audio or interaction logs to external services. Experiments in a laboratory smart-building testbed evaluate speech recognition robustness under varying noise levels, LLM command understanding accuracy and memory footprint, and end-to-end IoT task execution. The speech subsystem achieves a Word Error Rate of 5–20% depending on background noise. Across 33 IoT entities, the assistant reaches a 96.67% execution success rate with an average response time of 5.5 s. Among the evaluated local models, Qwen3 8B achieves the highest intent-to-action accuracy (Acc_I2A=100% on an oracle-text command test set with N=43) with 6.8 GB memory use. The results demonstrate that privacy-preserving and resilient voice interaction for smart building management is feasible using current local LLM stacks.
Evaluation of Permit-to-Work System for Confined Spaces Using Value Stream Mapping and Root Cause Analysis Aulia Nadia Rachmat; Nurul Ramadhanti; Arief Subekti; Adistia Puji Pramesti
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9356

Abstract

The work permit system fulfills clause 6.1.5 in PP No. 50 of 2012 concerning Occupational Health and Safety Management Systems (SMK3) and is required for high-risk activities, such as hot work, confined space operations, work at height, and scaffolding operations. This research aims to analyze waste in the confined space work permit issuance process and determined the root causes. The methods employed are Value Stream Mapping (VSM), to map the permit issuance workflow and identify existing waste. Root Cause Analysis (RCA), to analyze the root causes of waste. The results illustrate process efficiency of the confined space permit issuance process through Future State Mapping and recommendations for potential improvements to reduce waste permit issuance process, prevent work delays and avoiding impediments to company productivity. The waste analysis results of the confined space permit issuance process using Value Stream Mapping (VSM) indicate that the Approval 1 stage is already categorized as Lean Enterprise, with a Process Cycle Efficiency (PCE) value > 30%. However, the Approval 2 and Approval 3 stages are still classified as Un-Lean Enterprise, with PCE values < 30%. Recommended improvements include developing a notification-based website system, prioritizing new permit submissions, enabling mobile approvals, refining the permit issuance SOP and online submission process.
Rice Leaf Disease Classification Using Convolutional Neural Networks Enhanced with Convolutional Block Attention Module (CBAM) Muhamad Nanda Utama; Kusrini Kusrini
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9367

Abstract

Rice (Oryza sativa L.) is a staple food for over 270 million people in Indonesia, yet its productivity is continuously threatened by major diseases such as Tungro, Blast (Pyricularia oryzae), and Bacterial Leaf Blight (BLB), which can reduce yields by up to 70% and lead to crop failure. Traditional disease identification relies on manual visual observation, which is subjective, expertise-dependent, and inefficient for large-scale farming. This study aims to develop and compare four deep learning model variants ResNet-50, EfficientNet-B4,ResNet-50+CBAM,and EfficientNet-B4+CBAMfor automated classification of rice leaf diseases from digital images. A quantitative experimental approach was employed using a dataset of 5,702 images across four classes: Healthy, Tungro, Blast, and BLB. All models utilized transfer learning with ImageNet-pretrained weights, and the Convolutional Block Attention Module (CBAM) was integrated to enhance feature discrimination through channel and spatial attention mechanisms. The results demonstrate that ResNet-50 + CBAM achieved the best performance with 98.86% accuracy, 98.8% precision, 98.8% recall, and 98.8% F1-score, significantly outperforming the baseline ResNet-50 (50.6% accuracy). It can be concluded that the integration of CBAM with CNN architectures substantially improves classification accuracy by directing the model’s focus toward disease-relevant leaf regions while suppressing irrelevant background features. These findings provide a scalable and accurate diagnostic framework with strong practical implications for the development of mobile-based diagnostic tools to support real-time disease detection and precision agriculture decision-making by farmers in the field.
Phytochemical Analysis of Eco-Enzymes Combining Coffee Husks and Cocoa Husks Zuhrotul Mujayyanah; Melda Nurmaisari; Widia Rini Hartari; Supriyanto Supriyanto
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9379

Abstract

Eco enzyme is a multipurpose fermentation liquid made from organic materials. The purpose of this study was to determine the qualitative phytochemical content in eco enzyme samples combining coffee husks and cocoa husks. The ratio used for the solid organic material:sugar:water was 3:1:10. The treatment focused on variations in water substitutes with solid organic materials in the form of coffee husks and cocoa husks, as well as molasses as a sugar substitute. There were four types of treatments, namely E1 (Control), E2 (Coconut Water), E3 (Coffee Pulping Water), and E4 (Rice Washing Water). The types of phytochemicals tested were phenols, alkaloids, flavonoids, tannins, saponins, and cardenolins. The test results were observed based on the color changes that occurred. The phytochemical content detected in the eco enzyme sample is phenols, alkaloids, flavonoids, tannins, and saponins, while the cardenoline content was detected negatively.
Seismic Performance Enhancement of a Reinforced Concrete Building Using an RB-HDRC Base Isolation System Nur Khofifah; Ahmad Basshofi Habieb
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9398

Abstract

This study investigates the seismic performance enhancement of a four-story reinforced concrete building retrofitted with a Rubber Bearing-High Damping Rubber Core (RB-HDRC) base isolation system. A three-dimensional numerical model was developed and subjected to nonlinear time-history analysis under two design earthquake levesl (BSE 1-E and BSE 2-E). The results indicate that the base isolation system significantly reduces seismic demands compared to the fixed-base condition. Peak base shear was reduced by approximately 48% at the BSE-1E level and by 52% at the BSE-2E level. Roof acceleration decreased by about 76% and 79% at the BSE 1-E and BSE 2-E levels, respectively. The maximum interstory drift ratio was also reduced, demonstrating improved deformation control in the isolated system. Furthermore, the number of plastic hinges decreased significantly, while the energy dissipation capacity increased due to the hysteretic behavior of the RB-HDRC isolator. These findings demonstrate that RB-HDRC base isolation effectively enhances structural resilience and represents a promising strategy for improving the seismic performance of reinforced concrete buildings.
Quality Control Analysis at a Screen Printing Workshop Using the FMEA and Fuzzy FMEA Methods at UD. MKKG Gresik Restu Maulana; Deny Andesta
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9399

Abstract

UD. MKKG is a screen printing company facing product defect issues, such as ink not adhering, cracked prints, and imprecise results. This study aims to identify the primary causes of these defects and establish priorities for improving production quality in the screen printing unit. The research method used is the integration of Failure Mode and Effect Analysis (FMEA) with a Fuzzy approach to address subjectivity in risk assessment. Conventional RPN calculations showed the highest values for cracked prints (240), imprecision (150), and ink not adhering (75). The application of Fuzzy FMEA yielded more accurate and continuous FRPN values, namely cracked prints (249.5), imprecision (158), and ink not adhering (81.5). Proposed improvements include strict supplier selection, the use of periodic temperature thermometers, fabric pre-press techniques, and scheduling routine machine maintenance. The implementation of these steps is expected to minimize defective products and maintain customer confidence in product quality.
Hydraulic Capacity Analysis and Design of Road Culvert Drainage for Spillway Outflow in an Industrial Area in Pekalongan, Central Java, Indonesia Miskar Maini
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9402

Abstract

The development of industrial areas significantly increases surface runoff by expanding impervious surfaces, potentially exceeding the capacity of existing drainage systems and increasing flood risk. In many industrial zones, stormwater management infrastructure must also accommodate additional discharge from retention pond spillways, which can further burden road drainage systems. In the study area, spillway outflow from a retention pond is conveyed into the road drainage network, requiring an adequately designed culvert system to accommodate the flow safely. This study aims to analyze the hydraulic capacity and design an appropriate road culvert drainage system to convey spillway outflow in an industrial area. Secondary data on design flood discharge were obtained from previous studies that conducted rainfall frequency analysis, flood discharge estimation using the Nakayasu Synthetic Unit Hydrograph method, and spillway routing analysis. The results show that the design flood discharge for the 100-year return period (Q100) is 8.68 m³/s. A hydraulic analysis using the Manning equation was performed to determine the culvert dimensions required to convey the design discharge safely. The analysis indicates that the proposed culvert system is hydraulically adequate. A culvert with a diameter of 2.0 m is installed in the upstream section to accommodate concentrated inflow from the spillway outlet. In comparison, two parallel culverts with a diameter of 1.3 m are installed along the middle-to-downstream sections on both sides of the road. This configuration provides a total discharge capacity of 8.752 m³/s, exceeding the design flood discharge. The results demonstrate that the proposed design improves drainage Reliability in industrial areas and contributes to flood mitigation by regulating runoff discharge, thereby reducing potential flood risk in downstream residential areas. These findings provide practical guidance for infrastructure planning and policy strategies to integrate industrial drainage systems with regional flood mitigation efforts.
A Fuzzy FMEA-Based Approach for Risk Analysis in Car Body Spot Welding Processes Muhammad Miftahul Abid; Eka Rachmadi Endarta Putra; Andhyka Tyaz Nugraha; Tri Wisudawati
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9416

Abstract

The spot welding process using robotic systems is associated with a high risk of failure, including spot weld release, spatter, missed welds, unavailable weld spots, missing brackets, porous welds, double welds, incorrect weld positions, and sliding joint parts. This study aims to enhance risk assessment in spot welding by integrating fuzzy logic inference with Failure Mode and Effects Analysis (FMEA) to overcome the limitations of conventional FMEA in handling uncertainty and ambiguity. The proposed model incorporates fuzzy representations of severity, occurrence, and detection parameters to calculate the Fuzzy Risk Priority Number (FRPN) through three stages: fuzzification, fuzzy inference, and defuzzification. A case study was conducted in the spot welding process of automotive body components in Karawang, using real process data and expert validation. The results show that FRPN values range from 3.95 to 6.38, with the highest risks identified in spot weld release (FRPN = 6.38) and incorrect weld position (FRPN = 6.29), indicating that these failure modes are the top priorities for corrective actions. Furthermore, the fuzzy FMEA approach provides better discrimination of risk levels compared to conventional FMEA, particularly in differentiating failure modes with similar RPN values, thereby improving the accuracy and reliability of risk prioritization.
Forest Fire Detection Based on Digital Imagery Using Convolutional Neural Network (CNN) Model Candra Gudiato; Aditya Pratama; Christian Cahyaningtyas
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9422

Abstract

This study explores the implementation of a Convolutional Neural Network (CNN) for automated forest fire identification using digital image processing. Utilizing the USTC 'Forest Fire' dataset, the research framework involved systematic data preprocessing, including a 70:30 training-validation split and the application of image augmentation techniques to enhance model robustness. The proposed architecture features a sequential design with dual convolution and pooling layers, integrated with ReLU and Sigmoid activations. Although initial training over seven epochs yielded a deceptive validation accuracy of 99%, granular performance analysis exposed critical limitations. Evaluation via a Confusion Matrix revealed that while the model excelled at identifying 'non-fire' scenarios, it struggled significantly with actual fire detection, failing to recognize 301 out of 331 fire instances. These results highlight a severe class imbalance issue, suggesting that standard accuracy metrics are insufficient for this application and emphasizing the need for more balanced sampling or advanced architectural adjustments in future fire detection systems.

Page 92 of 93 | Total Record : 929

 89   90   91   92   93 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026 Vol 10 No 1 (2026): G-Tech, Vol. 10 No. 1 January 2026 Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025 Vol 9 No 3 (2025): G-Tech, Vol. 9 No. 3 July 2025 Vol 9 No 2 (2025): G-Tech, Vol. 9 No. 2 April 2025 Vol 9 No 1 (2025): G-Tech, Vol. 9 No. 1 January 2025 Vol 8 No 4 (2024): G-Tech, Vol. 8 No. 4 Oktober 2024 Vol 8 No 3 (2024): G-Tech, Vol. 8 No. 3 Juli 2024 Vol 8 No 2 (2024): G-Tech, Vol. 8 No. 2 April 2024 Vol 8 No 1 (2024): G-Tech, Vol. 8 No. 1 Januari 2024 Vol 7 No 4 (2023): G-Tech, Vol. 7 No. 4 Oktober 2023 Vol 7 No 3 (2023): G-Tech, Vol. 7 No. 3 Juli 2023 Vol 7 No 2 (2023): G-Tech, Vol. 7 No. 2 April 2023 Vol 7 No 1 (2023): G-Tech, Vol. 7 No. 1 Januari 2023 Vol 6 No 2 (2022): G-Tech, Vol. 6 No. 2 Oktober 2022 Vol 6 No 1 (2022): G-Tech, Vol. 6, No. 1, April 2022 Vol 5 No 1 (2021): G-Tech, Vol. 5, No. 1, Oktober 2021 Vol 4 No 2 (2021): G-Tech, Vol. 4, No. 2, April 2021 Vol 4 No 1 (2020): G-Tech, Vol. 4, No. 1, Oktober 2020 Vol 3 No 2 (2020): G-Tech, Vol. 3, No. 2, April 2020 Vol 3 No 1 (2019): G-Tech, Vol. 3, No. 1, Oktober 2019 Vol 2 No 2 (2019): G-Tech, Vol. 2, No. 2, April 2019 Vol 2 No 1 (2018): G-Tech, Vol. 2, No. 1, Oktober 2018 Vol 1 No 2 (2018): G-Tech, Vol. 1, No. 2, April 2018 Vol 1 No 1 (2017): G-Tech, Vol. 1, No. 1, Oktober 2017 More Issue