cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Yana Aditia Gerhana
Contact Email
yanagerhana@uinsgd.ac.id
Phone
+6285221512229
Journal Mail Official
yanagerhana@uinsgd.ac.id
Editorial Address
Jl. A.H. Nasution No. 105 Cibiru Kota Bandung
Location
Kota bandung,
Jawa barat
INDONESIA
ISTEK
Published by Universitas Islam Negeri Sunan Gunung Djati Bandung
ISSN : 19798911     EISSN : 30895081     DOI : https://doi.org/10.15575/istek.v13i2
Core Subject : Science, Agriculture, Engineering,
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Electrical & Electronics Engineering
ISTEK is a scientific journal that publishes research findings and theoretical studies focusing on the interaction between science, technology, and Islamic values. The journal aims to provide a platform for academics, researchers, and practitioners to share their discoveries and innovations that support the development of science and technology from an Islamic perspective.
Arjuna Subject : Umum - Umum
Articles 8 Documents
 1 
Search results for , issue "Vol. 14 No. 2 (2025)" : 8 Documents clear
THE EFFECT OF POLYVINYL PYROLYDONE (PVP), EXPLANT TYPE, AND EXPLANT PLANTING POSITION ON CALLUS GROWTH OF CIKONENG ST LARGE ORANGE (Citrus maxima (Burm.) Merr) AND SWEET ORANGE (Citrus sinensis (L.) Osbeck) Chaidir, Liberty; Pertiwi, Rahmi
ISTEK Vol. 14 No. 2 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i2.1339

Abstract

Cikoneng ST Orange (Citrus maxima (Burm.) Merr) is a germplasm of Sumedang area, which has been scarce for the past few years. The high percentage of browning in Cikoneng ST Orange explants is considered to be the cause of the low percentage of research success. Sweet Orange (Citrus sinensis (L.) Osbeck) is a type of orange that has been widely used as a potential orange explant in tissue culture. This study was conducted to determine the comparison of growth percentage by conducting cross-species research between Cikoneng ST Orange and Sweet Orange. The study was conducted at the Tissue Culture Laboratory of the Agrotechnology Department, Sunan Gunung Djati State Islamic University, Bandung from March to June 2017. The media used was a combination of MS media, 2 mg L-1 2.4 D, and 0.5% PVP. The explants used were leaves and leaf shoots of Cikoneng ST Orange and Sweet Orange. The planting positions of the explants included abaxial and adaxial planting positions. The study was analyzed using a descriptive method. The results showed that the administration of PVP in MS media and 2 mg L-1 2.4 D could induce callus of Sweet Orange at 3 DAI and Cikoneng ST Orange at 5 DAI. The use of leaf shoot explants and adaxial planting position produced the best friable callus up to 28 DAI. This study also found that Sweet Orange had the fastest callus growth time and a low browning percentage compared to Cikoneng ST Orange explants.
Analysis of Critical Factors Influencing Online Motorcycle Taxi Driver's Income Per Transaction Using Random Forest Regressor And Feature Importance Wahana, Agung; Alam, Cecep Nurul
ISTEK Vol. 14 No. 2 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i2.2338

Abstract

This study aims to identify and measure the main factors that most significantly affect the Income of Online Motorcycle Taxi Drivers Per Transaction in the gig economy sector. The Machine Learning Random Forest Regressor algorithm was used on driver transaction data. This methodology was chosen for its ability to handle the data's non-linearity and to objectively measure Feature Importance. Traditional linear regression models have limitations in these areas. The main results show the Random Forest model is highly accurate (R2 = 0.9634). It confirms the absolute dominance of distance, which accounts for 94.98% of the total predictive importance of revenue. The Total Transaction Value factor (3.82%) is a secondary predictor. Demographic variables (Age and Gender) and temporal variables (Days and Hours) together had a minimal (less than 1%) influence on fare per trip. This research concludes that the rate per driver transaction is determined almost exclusively by the platform's distance-based pricing policy. It is neutral to the characteristics of the driver. These findings recommend that platforms focus on increasing order volume and optimizing operational costs, rather than modifying base rates.
Application of Chitosan from Crab Shell Waste (Portunus pelagicus) as a Preservative for Muli Bananas (Musa acuminata L) Yusmargana, Fuji Astuti; Kurniasih, Nunung; Junitasari, Assyifa
ISTEK Vol. 14 No. 2 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i2.2396

Abstract

Crab shell is one of the wastes generated from the marine product processing industry. However, the utilization is still very low, especially in Cirebon, it is only used as animal feed and even most of it is waste that also pollutes the environment. One of the alternatives for processing crab shells is used as chitosan because the crab shells are rich in chitin. Chitosan is a chitin derivative compound resulting from the deacetylation process. Chitosan can be called a biopolymer that contains the most nitrogen in nature and also has anti-bacterial, non-toxic, and biodegradable properties because this is why chitosan is in great demand in the industry. Chitosan has a very diverse potential such as in the environmental, pharmaceutical and food fields, one of which has the potential to be a safe preservative in food. This study aims to utilize crab shell waste into chitosan as a preservative for Muli bananas. This research is an experimental study using a completely design with six stages including demineralization, deproteination, deacetylation, manufacture of coating solutions with various concentrations (0%, 1%, 1.5%, 2% and 2.5%), coating process and testing. physical. The parameters measured were the degree of deacetylation, the effect of chitosan concentration and physical tests (discoloration). The results showed that the degree of deacetylation of the chitosan obtained was 95.9825%. From the results of the physical test, it was found that the addition of chitosan with concentrations of 1%, 1.5%, 2% and 2.5% in the coating process resulted in the greater concentration of chitosan being added, the longer the ripening process in bananas and causes bananas peels are not easy to brown.
Numerical Simulation of Fluid Flow on An Open Channel with Parabolic Cross-section Erianto, Elvi Syukrina; Aprilia, Nadya Zulfani; Khumaeroh, Mia Siti
ISTEK Vol. 14 No. 2 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i2.2447

Abstract

Water is a vital resource whose movement is influenced by various factors such as gravity and frictional force. The cross-sectional shape of a channel can significantly influence the friction force,consequently, affect the flow characteristics. One of the interesting cross-sectional shapes to analyze is parabolic because of its unique geometric properties. This study aims to conduct a numerical simulation of open channel flow within a parabolic cross-section using a modified Shallow Water Equation and the Finite Volume Method implemented with a staggered grid scheme. The mathematical model used takes into account the influence of the parabolic shape through the calculation of Manning's friction, which depends on the hydraulic radius. The Shallow Water Equations, consisting of the continuity and momentum equations, are solved numerically through spatial and temporal discretization. The simulations are perfomed using Scilab to generate visualizations of the water depth and flow velocity distribution under various geometric conditions. This study produces simulations of one-dimensional (1D) and two-dimensional (2D) dam-break flows with a parabolic cross section and compares them with the rectangular cross-section. The simulation results show that the finite volume method with the staggered grid scheme provides stable solutions and is capable of accurately describing the flow behavior across different channel geometries.
Desain dan Implementasi Sistem Instrumentasi Aliran Fluida Berbasis Supervisory Control And Data Acquisition (SCADA) dan dan Programmable Logic Controller (PLC) Hasna Humaira, Raden Roro; Zaki Hamidi, Eki Ahmad; Ridwan, Azwar Mudzakkir
ISTEK Vol. 14 No. 2 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i2.2575

Abstract

One of the main challenges in the development of instrumentation systems for industrial fluid flow processes is the requirement for real-time pressure monitoring and control to prevent abnormal conditions that may lead to operational failures. This study aims to design and develop an instrumentation system capable of performing monitoring, control, and early warning functions through the integration of a pressure transmitter, Haiwell AC12M0R PLC, HMI, and SCADA using TCP/IP and Wi-Fi communication protocols. The system design includes hardware development, ladder diagram programming, and configuration of a cloud-connected HMI–SCADA interface. System testing was conducted by varying pressure setpoints to simulate different operating conditions. The test results indicate that the system operates as designed, as evidenced by alarm activation at a pressure of 6 bar, proportional opening of the Pressure Control Valve (PCV) when the pressure exceeds the 5 bar setpoint, and activation of safety functions under high-high pressure conditions at 9 bar, where the system triggers an alarm, closes the Shut Down Valve (SDV), and automatically stops the pump. The PCV response time was recorded at 0.1–0.2 seconds, while the SDV fully closed within 5–6 seconds. All process data can be monitored in real time through the HMI and cloud-integrated SCADA system, enabling remote monitoring via smartphone. Overall, the developed instrumentation system prototype functions in accordance with the control logic and performs reliably under the simulated operational scenarios.
MOVIE RATING PREDICTION USING NEURAL FACTORIZATION MACHINES (NFM) APPROACH Khairani, Jessy Faujiyyah; Zulfikar, Wildan Budiawan; Lukman, Nur
ISTEK Vol. 14 No. 2 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i2.2598

Abstract

This research is motivated by the difficulty viewers have in finding movies that suit their tastes amid the large number of movies being produced. Current movie ratings are often based solely on direct assessments by viewers without considering factors such as genre, audience age category, and movie synopsis. This study aims to predict movie ratings using the Neural Factorization Machines (NFM) approach. The research method includes data preparation, which covers dataset file merging, age category mapping, data cleaning, text conversion to lowercase, regular expression removal, removal of non-English text, tokenization, lemmatizing, word embedding, one-hot encoding, and label encoding. The modeling process was carried out by building an NFM model consisting of feature inputs, embedding layers, bi-interaction layers, hidden layers, and prediction scores. Model evaluation was carried out by setting hyperparameters, namely epoch and batch size, to optimize model performance. This study was conducted with 9 tests using a combination of epochs (30, 50, and 100) and batch sizes (64, 128, and 256). The evaluation results show that the lowest MSE value, which means the best, in the training data is 1.181 with a batch size of 256 and an epoch of 100, and in the validation data is 1.230 with a batch size of 256 and an epoch of 100. However, in the test data, the configuration with a batch size of 128 and 50 epochs gave the best MSE of 1.280. Although the model showed the best performance in the training and validation data with a batch size of 256 and 100 epochs, the evaluation graph indicated overfitting. These findings show that the NFM model is capable of predicting movie ratings based on genre, audience age category, and movie plot description.
Transforming Story Ideas from Images to Text Using Convolutional Neural Networks (CNN) and Generative Pre-trained Transformer (GPT-2) Rizqullah, Moh Hasbi; Nurlatifah, Eva; Budiawan Zulfikar, Wildan
ISTEK Vol. 14 No. 2 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i2.2599

Abstract

The gap between rich visual inspiration and the challenge of creative articulation (writer’s block) remains a major obstacle in the writing process. This study aims to bridge this gap by designing a two-stage artificial intelligence system based on deep learning to provide automated narrative stimuli. The proposed method implements a custom Convolutional Neural Network (CNN) architecture to detect seven classes of natural objects from 4,362 images. The detected objects are then used as prompts for a fine-tuned Generative Pre-trained Transformer (GPT-2) model to generate poetic narratives. Experimental results indicate that the CNN module achieved a peak classification accuracy of 61.96%. Confusion matrix analysis reveals that this limitation is not caused by overfitting, but rather by high inter-class visual ambiguity. Although the GPT-2 module is capable of generating narratives with a BERT Score F1 of up to 0.6455, the primary finding of this study is that the overall narrative quality is highly dependent on the accuracy of the CNN output, which acts as a critical bottleneck in the system.
THE EFFECTIVENESS OF INQUIRY-BASED LEARNING IN PROXIMITY SENSOR PRACTICUM TO IMPROVE STUDENT UNDERSTANDING Syafar Farouk, Irfan; Sulistiani, Fitria Ayu; Chusni, Muhammad Minan; Kariadinata, Rahayu; Sanjaya, Mada
ISTEK Vol. 14 No. 2 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i2.2604

Abstract

Laboratory practicum is essential for understanding abstract concepts, and the Inquiry Based Learning model is often applied in this context. This study aims to measure the level of effectiveness of implementing inquiry based learning in an electronics practicum on analog proximity sensor material towards improving student concept understanding. This study uses a quantitative approach with a One-group pretest-posttest design involving 27 3rd-semester students from the Physics Department of UIN Sunan Gunung Djati Bandung. Data were analyzed using the Shapiro-Wilk normality test, hypothesis testing (paired t-test), and N-Gain analysis. The results showed that the pre-test (Sig. 0.054) and post-test (Sig. 0.089) data were normally distributed. The t-test showed a very significant difference (Sig. 0.000) between the pre-test (46.29) and post-test (73.70) mean scores. Despite a significant increase, the N-Gain Percent analysis showed an average effectiveness of 51.93%, which falls into the "Less Effective" category. There was a high disparity in results, where 37% of students were still "Not Effective". Factors such as the diversity of students' prior knowledge, material complexity, and guidance effectiveness were identified as causes for the non-optimal effectiveness. This study concludes that inquiry based learning needs to be integrated with differentiated learning). 

Page 1 of 1 | Total Record : 8

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 14 No. 2 (2025) Vol. 14 No. 1 (2025) Vol. 13 No. 2 (2024): Desember 2024 Vol. 13 No. 1 (2024): Juni 2024