cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Paska Hasugian
Contact Email
infokum@seaninstitute.org
Phone
+6281264451404
Journal Mail Official
infokum@seaninstitute.org
Editorial Address
Komplek New Pratama ASri Blok C, No.2, Deliserdang, Sumatera Utara, Indonesia
Location
Unknown,
Unknown
INDONESIA
INFOKUM
Published by SEAN INSTITUTE
ISSN : 23029706     EISSN : 27224635     DOI : -
Core Subject : Science,
Computer Science & IT
The INFOKUM a scientific journal of Decision support sistem , expert system and artificial inteligens which includes scholarly writings on pure research and applied research in the field of information systems and information technology as well as a review-general review of the development of the theory, methods, and related applied sciences. Software Engineering. Image Processing Datamining Artificial Neural Networks
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 891 Documents
 86   87   88   89   90 
A Hybrid GRU-BiLSTM Deep Learning Framework for Solar Radiation Forecasting and Photovoltaic Energy Yield Assessment in Timor Island, Indonesia Yobel Eliezer Mahardika; Agustina Rachmawardani; Marzuki Sinambela
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3133

Abstract

Timor Island in East Nusa Tenggara possesses abundant solar energy resources, yet the technical feasibility of solar power plant (PLTS) development in the region has rarely been assessed using data-driven quantitative methods. This study aims to develop and validate a hybrid GRU-BiLSTM deep learning model for short-term solar radiation forecasting, to assess whether this model can be reliably extended into long-horizon autoregressive projection, to estimate the solar radiation potential and photovoltaic energy production across five locations in Timor Island, and to characterize the radiation variability relevant to PLTS design. A hybrid GRU-BiLSTM deep learning model was developed and evaluated for short-term hourly solar radiation forecasting using ERA5 reanalysis data (2015-2025), achieving R² of 0.9507-0.9584 across five locations. Because chained autoregressive projection using this model was found to be unreliable for annual-horizon estimation (R² = -0.53, +46% overestimation), a climatological approach based on 2015-2025 historical averages was applied instead for potential assessment. The results show that the five locations possess high and relatively uniform solar potential, with annual totals ranging from 2,023 to 2,109 kWh/m² (5.54-5.78 kWh/m²/day), corresponding to estimated photovoltaic energy production of 273.1-284.8 kWh/m² per year. Coefficient of variation values (69.6-71.0%) indicate substantial short-term fluctuation despite the locations' consistent seasonal pattern, with the lowest production occurring in June and the highest in October. These findings provide a quantitative basis for PLTS capacity planning and energy storage design in Timor Island, demonstrating that a validated short-term forecasting model can be meaningfully extended into practical renewable energy resource assessment.
The Effect of Paclobutrazol Concentration on the Growth and Production of Several Varieties of Mung Beans (Vigna radiata L.) Aisyah Br Sembiring; Ariani Syahfitri Harahap; Suryani Sajar
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3134

Abstract

This study aims to determine the effect of paclobutrazol concentration on the growth and production of several varieties of mung bean (Vigna radiata L). This study used a factorial Randomized Block Design (RBD) with paclobutrazol concentration treatments (0, 10, 20, and 30 ppm) and mung bean varieties (Vima 2, Kutilang, and Vimil 1). The parameters observed in this study were plant height, flowering age, number of productive branches, number of pods per sample, number of pods per plot, seed weight per sample, seed weight per plot, weight of 100 seeds per plot, and root length. The results showed that the administration of paclobutrazol concentration significantly affected the parameters of plant height 2, and 5 WAP, flowering age, number of productive branches, number of pods per sample, number of pods per plot, seed weight per sample, seed weight per plot, and root length, and did not significantly affect the parameters of plant height 3, 4 WAP and weight of 100 seeds per plot, and the variety treatment showed a significant effect on the parameters of plant height 2, 3, 5 WAP, number of productive branches, number of pods per sample, number of pods per plot, seed weight per sample, seed weight per plot, weight of 100 seeds per plot, and root length and did not significantly affect the parameters of plant height 4 WAP flowering age. and the interaction between the two concentrations had no significant effect. The concentration of paclobutrazol at 20 ppm and the Kutilang variety showed a significant effect on the growth and production of mung bean plants.
Optimization of Time and Air Flow Speed of Densitometric Table Machine (Sutton) Towards the Efficiency of Separation of Arabica Coffee Beans Ready for Export Daffa Alfinsyah; Andi Setiawan; Desi Sri Pasca Sari Sembiring
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3135

Abstract

The physical quality of Arabica coffee beans is a key determinant of product competitiveness in the export market. One common problem is the presence of hollow beans (trieste), which can reduce the quality and economic value of the coffee. Therefore, an effective sorting process utilizing a Sutton-type densitometric table is necessary. This study aims to analyze the effect of airflow velocity and sorting time and determine the optimal treatment combination to improve the separation performance of hollow coffee beans. This study used a factorial Randomized Block Design (RBD) with two treatment factors, namely air flow speed consisting of three levels (low, medium, and high) and sorting time consisting of three levels (1 hour, 2 hours, and 3 hours). Each treatment combination was repeated twice to obtain nine treatment combinations. The parameters observed included engine capacity, air flow stability, and the level of purity of the sorting results. Data were analyzed using analysis of variance (ANOVA) at a significance level of 5% and continued with the Duncan test. The results showed that variations in airflow velocity and sorting time had a highly significant effect (p<0.05) on all observed parameters. The best treatment combination was obtained at A3W3 (high airflow velocity with a sorting time of 3 hours), which resulted in a machine capacity of 230 kg/hour, airflow stability of 14.90, and a purity level of 100%. In general, increasing airflow velocity followed by increasing sorting time tends to increase the effectiveness of the process of separating hollow coffee beans.
Monitoring Electrical Charge Overflow During Voltage Conditions as a Preventive Measure for Preventing Disturbances in 20kv Feeder at PT PLN (Persero) ULTG Nias Roy Christian Siregar; Hamdani Hamdani; Siti Anisah
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3136

Abstract

The reliability of 20 kV feeders is greatly influenced by the condition of the equipment and the insulation system that operates continuously. One of the causes of disturbances in the distribution network is the occurrence of electrical overflow (partial discharge) which can develop into equipment damage if not detected early. This study aims to analyze the application of electrical overflow monitoring during voltage conditions as a preventive measure to prevent disturbances in 20 kV feeders at PT PLN (Persero) ULTG Nias. The research method was carried out through online partial discharge measurements using the Ultra TEV Plus 2 tool in the GB2, GB3, and GB4 feeder cubicles without performing a system shutdown. The data obtained were analyzed based on the parameters of Transient Earth Voltage (TEV), Pulse Per Cycle (PPC), and ultrasonic measurements to determine the level of potential disturbances in the equipment. The measurement results showed that the GB2 and GB3 feeders had a TEV value of 5 dB with a PPC of 0 so that they were included in the normal category and did not show any indication of partial discharge activity. Meanwhile, on the GB4 feeder, a TEV value of 20 dB with a PPC of 1.83 was obtained, and a hissing sound was detected in ultrasonic measurements, indicating the presence of medium-level partial discharge activity due to a decrease in insulation quality. The results of the study prove that monitoring electrical discharge overflows under voltage conditions can identify potential disturbances early so that maintenance actions can be carried out appropriately and planned to improve feeder reliability and maintain the continuity of electricity distribution.
Safety Analysis of the Grounding System at the 150 kV Simpang Haru Substation Using the Grid Grounding System Method Based on the IEEE Std 80 Standard Danil Danil; Hamdani Hamdani; Siti Anisah
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3137

Abstract

The grounding system at the substation is an important part of the electric power system that functions to maintain the safety of humans and equipment against ground fault currents. A grounding system that does not meet standards can cause touch voltages and step voltages that are dangerous for personnel and electrical equipment. This study aims to analyze the safety of the grounding system at the 150 kV Simpang Haru Substation using the Grid Grounding System method based on the SPLN and IEEE Std 80 standards. The analysis was carried out by calculating the grounding grid resistance value, Ground Potential Rise (GPR), touch voltage, and step voltage. The research data were obtained from the technical data of the substation grounding system including soil resistivity, grounding grid area, conductor length, and single-phase ground fault current. The results showed that the grounding resistance value of 0.49 Ω still meets the SPLN standard, which is below 1 Ω. The Ground Potential Rise value obtained was 5.88 kV. The touch voltage of 96 Volts and the step voltage of 36 Volts are still below the IEEE Std 80 safety limits of 638 Volts and 2,204 Volts, respectively. Based on the results of the analysis, the grounding system at the Simpang Haru 150 kV Substation is declared safe and meets safety standards based on SPLN and IEEE Std 80.
Recloser Installation for Distribution Network Reliability at the Christmas Party Jefri Ardiansyah; Hamdani Hamdani; Pristisal Wibowo
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3139

Abstract

The reliability of the electricity distribution system is one of the important indicators in assessing the quality of electricity service to customers. The YB.02 feeder located in the working area of ​​PT PLN (Persero) ULP Natal has a network length of 297 km with a total of 11,820 customers and uses a radial network configuration. Disturbances that occur in the downstream area of ​​the feeder have the potential to cause blackouts to a large number of customers, thereby reducing the level of reliability of the distribution system. One of the efforts made to improve network reliability is the installation of Natal Reclosers in Section 8 in the Simpang Pulopadang area. This study aims to analyze the effect of recloser installation on improving the reliability of the distribution network at the YB.02 Feeder. The research method used is a descriptive quantitative method by analyzing disturbance data, the number of affected customers, the duration of blackouts, and the SAIFI and SAIDI reliability indices before and after the recloser installation. The results showed that before the recloser installation, the SAIFI value was 3.30 times/customer/year and the SAIDI was 7.13 hours/customer/year. After the installation of the Natal Recloser, the SAIFI value decreased to 1.12 hours/customer/year and the SAIDI value decreased to 1.02 hours/customer/year. The installation of the recloser was also able to reduce the disturbance area which previously affected around 7,800 customers to around 2,300 customers in the affected section. In addition, the autoreclose function is able to automatically overcome temporary disturbances so that the frequency and duration of blackouts can be minimized. The results showed that the installation of the Natal Recloser was able to reduce the SAIFI value by 66.06% and SAIDI by 85.69%, so it is effective in improving the reliability of the distribution network and continuity of electricity services to customers in the working area of ​​PT PLN (Persero) ULP Natal.
Inductive Load Analysis of a 15 HP Induction Motor A Case Study on Energy Efficiency and Power Factor Correction in a Palm Oleo Processing Plant Agus Supriyadi; Rahmaniar Rahmaniar; Zuraidah Tharo
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3140

Abstract

This study aims to analyze the impact of inductive loads on the performance of a three-phase power system using a 15 HP induction motor and to evaluate the effectiveness of power factor correction in improving energy efficiency. The research employs a mathematical analysis approach based on a three-phase power system model by considering active power, reactive power, apparent power, current, and power losses under load variations of 50%, 75%, and 100%. The results indicate that the power factor decreases under partial-load conditions, reaching as low as 0.66, which leads to higher current demand and increased power losses. Following power factor correction using a 5 kVAR capacitor bank, the power factor improved to 0.95. This improvement resulted in approximately a 14% reduction in system current and a decrease in power losses of 192 W. Furthermore, the reduction in reactive power consumption lowered the kVARh-to-kWh ratio, thereby eliminating the potential utility penalty charges associated with excessive reactive energy usage. Overall, the findings demonstrate that power factor correction is an effective solution for enhancing energy efficiency, improving power system performance, and reducing operational costs in industrial systems driven by induction motors.
Analysis of Battery Energy Storage Capacity on Load Operating Duration in a 50 WP Portable Solar Power System Bona Valti Marpaung; Erpandi Dalimunthe; Haris Gunawan
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3141

Abstract

Limited access to electrical energy in remote areas requires alternative energy solutions, one of which is a portable solar power system (PLTS). One of the key components affecting system performance is the battery, which functions as energy storage.This study aims to analyze the effect of battery energy storage capacity on the duration of load usage in a 50 Wp portable solar power system. The research method used is experimental, including system design, component selection, assembly, and performance testing. The system consists of a 50 Wp solar panel, MPPT solar charge controller, 12 V 20 Ah battery, inverter, and LED load. Testing was conducted by observing battery voltage and load operating duration. The results show that the battery is capable of supplying a load of 35 W for approximately ±6 hours. The system operates stably with gradual voltage decline. Therefore, battery capacity significantly influences the duration of load usage.
Multifunctional Building Design with a Green Architecture Approach in Medan City Muhammad Abdillah Sm; Dara Wisdianti; Peranita Sagala
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3143

Abstract

The population growth of Medan City, which will reach 2.54 million people in 2024, puts significant pressure on the city's infrastructure needs, especially vertical housing, commercial space, and efficient workspaces. The limited urban land encourages the need for a multifunctional building design approach that is able to integrate several functions in one integrated area. This research aims to design a multifunctional building that combines the functions of shopping malls, apartments, and rental offices by applying a green architecture approach as the main design strategy. The method used is a descriptive-qualitative method through literature study, site analysis. The green architecture approach is applied through the integration of vertical gardens on the façade, lighting and natural ventilation systems, the use of environmentally friendly materials, and efficient water and energy management. The design results show that the integration of the three functions in one 14-story building is able to maximize vertical land use while creating a built environment that is responsive to the tropical climate of Medan City. The façade of the building is designed with a double façade system and a green layer that functions as a solar heat filter as well as an architectural aesthetic element. The conclusion of this study shows that the green architecture approach in multifunctional buildings not only improves environmental quality, but also provides economic and social added value for the urban areas of Medan City.
Machine Learning-Based Customer Segmentation for Mobile Banking Services using K-Means Clustering Indra Syah Putra; Alex P Karo Karo; Feri Ranja; Roswhita Bukit; Joceline Schellenberg W
INFOKUM Vol. 14 No. 94 (2026): Infokum 2026
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v14i94.3144

Abstract

This study aims to segment customers based on 2024 m-banking transaction data at a regional bank in North Sumatra using the K-Means Clustering algorithm. The research process follows the CRISP-DM stages, including data preparation, data mapping, data cleaning, and clustering using Python. From 1,035,184 transaction data, 1,024,767 valid data were obtained, grouped into several service categories (e-wallet, internet, electricity & water, and insurance). The clustering results show different customer behavior patterns in each category, ranging from micro customers with small transactions and high frequency, regular customers with medium transactions, to premium customers with large transaction values ​​but low frequency. The results of this segmentation can help banks design more targeted marketing strategies, improve operational efficiency, and support data-based fraud detection systems.

Page 89 of 90 | Total Record : 891

 86   87   88   89   90 

Filter by Year

2018 2026


Reset
Filter By Issues
All Issue Vol. 14 No. 94 (2026): Infokum 2026 Vol. 14 No. 03 (2026): Infokum, May - June 2026 Vol. 14 No. 02 (2026): Infokum, March-April 2026 Vol. 14 No. 01 (2026): Infokum, January - February 2026 Vol. 13 No. 06 (2025): Infokum Vol. 13 No. 05 (2025): Infokum Vol. 13 No. 04 (2025): Infokum Vol. 13 No. 03 (2025): Infokum Vol. 13 No. 02 (2025): Infokum Vol. 13 No. 01 (2025): Infokum Vol. 12 No. 04 (2024): Engineering, Computer and Communication, November 2024 Vol. 12 No. 01 (2024): Engineering, Computer and Communication, Edition January 2024 Vol. 11 No. 05 (2023): Engineering, Computer and Communication Vol. 11 No. 04 (2023): Agustus : Engineering, Computer and Communication Vol. 11 No. 03 (2023): Juni : Engineering, Computer and Communication Vol. 11 No. 02 (2023): April, Engineering, Computer and Communication Vol. 10 No. 03 (2022): August, Data Mining, Image Processing, and artificial intelligence Vol. 10 No. 02 (2022): Juni, Data Mining, Image Processing, and artificial intelligence Vol. 10 No. 5 (2022): December, Computer and Communication Vol. 10 No. 4 (2022): October, computer, information and engineering Vol. 10 No. 1 (2021): Desember, Data Mining, Image Processing, and artificial intelligence Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence Vol. 9 No. 1,Desember (2020): Data Mining, Image Processing,artificial intelligence, networking Vol. 8 No. 2, Juni (2020): Data Mining, Image Processing and artificial intelligence Vol. 8 No. 1, Desembe (2019): Data Mining,Image Processing and artificial intelligence Vol. 7 No. 2, Juni (2019): Data Mining And Image Processing Vol. 7 No. 1, Desembe (2018): Data Mining And Image Processing More Issue