Article Per Year (5 Year)
p-Index From 2021 - 2026
7.217
P-Index
This Author published in this journals
All Journal ComEngApp : Computer Engineering and Applications Journal Transmisi: Jurnal Ilmiah Teknik Elektro Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Jurnal technoscientia Prosiding SNATIF Teknika: Jurnal Sains dan Teknologi Prosiding Semnastek Scientific Journal of Informatics Proceeding SENDI_U SMATIKA Jurnal Ampere JURNAL NASIONAL TEKNIK ELEKTRO PROtek : Jurnal Ilmiah Teknik Elektro JETT (Jurnal Elektro dan Telekomunikasi Terapan) JURNAL MEDIA INFORMATIKA BUDIDARMA VOLT : Jurnal Ilmiah Pendidikan Teknik Elektro Indonesian Journal of Artificial Intelligence and Data Mining INOVTEK Polbeng - Seri Informatika Jurnal Teknologi Sistem Informasi dan Aplikasi Jurnal RESISTOR (Rekayasa Sistem Komputer) Patria Artha Technological Journal EDUMATIC: Jurnal Pendidikan Informatika Jurnal Qua Teknika Jurnal Fokus Elektroda : Energi Listrik, Telekomunikasi, Komputer, Elektronika dan Kendali Building of Informatics, Technology and Science Jurnal Informatika dan Rekayasa Elektronik JURNAL TEKNOLOGI TECHNOSCIENTIA Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Jurnal Teknik Informatika (JUTIF) Fokus Elektroda: Energi Listrik, Telekomunikasi, Komputer, Elektronika dan Kendali) Jurnal Pendidikan dan Teknologi Indonesia Aptekmas : Jurnal Pengabdian Kepada Masyarakat Jurnal Ilmiah Teknik Elektro Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Emitor: Jurnal Teknik Elektro INOVTEK Polbeng - Seri Informatika Smatika Jurnal : STIKI Informatika Jurnal ITEJ (Information Technology Engineering Journals)
Sopian Soim, Sopian
Politeknik Negeri Sriwijaya
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Public Health Social Sciences Transportation Veterinary Other

Published : 72 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 72 Documents
Search

 4   5   6   7   8 
CNN ALGORITHM OPTIMIZATION FOR CLASSIFYING NUMBERS IN HANDWRITING Septiani, Dinda; Fadhli, Mohammad; Soim, Sopian
Transmisi: Jurnal Ilmiah Teknik Elektro Vol 27, No 1 Januari (2025): TRANSMISI: Jurnal Ilmiah Teknik Elektro
Publisher : Departemen Teknik Elektro, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/transmisi.27.1.57-63

Abstract

Handwritten numeral recognition is an important challenge in image processing, with wide applications in areas such as document processing and data automation. This research aims to optimize the performance of Convolutional Neural Network (CNN) model in classifying handwritten numerals on MNIST dataset. In this research, experiments were conducted with variations in the number of CNN layers to evaluate their effect on model accuracy. The results show that the model with 4 convolutional layers achieves the highest accuracy of 92.41%, which signifies a significant improvement in the model's ability to extract important features from the image compared to the model with fewer layers. This research also applied the best model to a website that allows users to recognize handwritten numerals in real-time. This provides practical benefits in the development of automatic character recognition systems and shows how this technology can be applied directly in everyday life.
Rancang Bangun Sistem Pemantau Penerima Sinyal Automatic Dependent Surveillance-Broadcast (ADS-B) Berbasis Raspberry Pi dan Antena Ground Plane Sebagai Antena Penerima Maharani, Fistania Ade Putri; Soim, Sopian; Fadhli, Mohammad
PROtek : Jurnal Ilmiah Teknik Elektro Vol 9, No 2 (2022): Protek : Jurnal Ilmiah Teknik Elektro
Publisher : Program Studi Teknik Elektro Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/protk.v9i2.4690

Abstract

Currently, the technology used for aircraft monitoring is Radar technology. Radar's accuracy is hampered, however, by the fact that while an aircraft is airborne or in flight, it is frequently obscured by clouds, making it difficult to detect the aircraft. Due to constraints in radar technology, Automatic Dependent Surveillance-Broadcast technology was developed to improve the performance of air navigation security. Raspberry Pi, RTL-SDR, and LNA were used as the research method in designing the ADS-B signal receiver monitoring system. The 1090 MHz Ground Plane Antenna is preferable because it has a higher gain and a radiation pattern influenced by radial elements, allowing it to collect a considerably broader signal when combined with Raspberry Pi RTL-SDR and LNA. The monitoring results based on the test data are impressive, generating six aircraft simultaneously, indicating that dump 1090 is very effective at translating the aircraft's ADS-B signal data emitted every 0.5 seconds. ICAO, Altitude and Longitude information are clear Based on tests, the aircraft's ADS-B signal was identified between 4,000 and 38,000 feet over the maximum value, causing the signal to disappear and fail to decode the information. The maximum distance measured during the test was 49.7 kilometers from the elevated location where the ADS-B signal monitoring device was installed. The results of the first test were placed 10 meters above the ground. The result is significantly better than the short antenna position. This significantly improves the accuracy of the ADS-B signal monitoring system and the synchronization of information exchange through real-time monitoring.
Link Budget Prediction at 28 GHz Frequency Based on Rain Attenuation Model in Palembang City Tarnita Rizky Prihandhita; Soim, Sopian; Fadhli, Mohammad
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/apvf0b18

Abstract

5G communication technology brings a major leap in the development of wireless networks, especially through the utilization of millimeter wave frequencies. However, mmWave signals are very susceptible to rain attenuation, which can significantly reduce the quality of 5G services. This study aims to estimate how much signal loss and reception power there will be for 5G at a frequency of 28 GHz in Palembang City and to examine how rain affects the mmWave signals. MATLAB simulations use Palembang rainfall data for the March 2025 period and use the ITU-R P.618-5 rain attenuation model, Simple Attenuation Model, and ITU-R Tropical. Using the Urban Macro propagation scenario in line-of-sight and non-line-of-sight conditions. The results show that distance and rainfall affect signal attenuation, with NLOS conditions producing worse attenuation than LOS. At high rainfall of 84.5 mm/hour in NLOS conditions, ITU-R P.618-5 predicts the highest total path loss of about 317 dB, ITU-R Tropical about 247 dB, and SAM about 227 dB. With the received power of ITU-R P.618-5 model of -260 dBm, ITU-R Tropical of -190 dBm, and SAM of -170 dBm.
Analysis of Openwrt-Based X86 Router Performance in Bandwidth Management on Local Internet Network Alqhaniyyu, Faris; Soim, Sopian; Zakuan Agung, Muhammad
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 3 (2025): November
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/h7m8mz76

Abstract

This research aims to analyze the performance of OpenWRT-based x86 routers in local network bandwidth management through the application of Quality of Service (QoS), traffic shaping, and rate limiting features based on NFTables. Testing was conducted directly on the local network of Muara Merang Village for two weeks using an x86 mini PC as the main router. Data was collected using Wireshark and Ping to measure throughput, latency, jitter, and packet loss parameters before and after QoS configuration. The results showed an increase in VoIP service throughput from 950 Kbps to 1,296 Kbps (±36% increase), latency dropped from 38 ms to 3 ms (±92% decrease), jitter from 18 ms to 6 ms, and packet loss reduced from 2.5% to 0%. While on 4K streaming services, throughput increased from 19 Mbps to 27 Mbps (±42% increase), latency dropped from 63 ms to 47 ms, and jitter from 55 ms to 47 ms, with total elimination of packet loss. This study makes a novel contribution by testing the effectiveness of QoS on x86 architecture-based OpenWRT in a local context that has rarely been objectified before, in contrast to previous studies that predominantly used ARM/MIPS architecture and small network scenarios. The findings reinforce the potential of combining OpenWRT and x86 devices as an adaptive and cost-effective networking solution for MSMEs, educational institutions, and digital communities in infrastructure-constrained regions.
Implementation of 5G Standalone Private Network for UHD Video Streaming Adriansyah, Ahmad; Soim, Sopian; Aryanti
Emitor: Jurnal Teknik Elektro Vol 25, No 2: July 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/emitor.v25i2.11093

Abstract

The growing user preference for Ultra High Definition (UHD) video content on various Over-the-Top (OTT) platforms presents a significant challenge in Indonesia, where 5G network coverage is limited and primarily based on the Non-Standalone (NSA) architecture. This study demonstrates the development and implementation of an affordable private 5G Standalone (SA) network as a viable alternative for high-quality video streaming. A private 5G SA network was constructed using open-source Open5GS software and a Universal Software Radio Peripheral (USRP) B210. Its performance was evaluated through speed tests and traffic sniffing analysis during 4K and 8K video streaming and then compared against a public 5G NSA network in Palembang. The results showed that the private SA network delivered significantly faster upload speeds and more consistent low latency than its public NSA counterpart. Although some public NSA locations provided higher download speeds, both network configurations achieved flawless data transmission with zero packet loss and high throughput during UHD streaming. The study concludes that a private 5G SA network is a highly effective, flexible, and slightly superior alternative for deployment, capable of reliably supporting the demands of UHD video streaming.
Design and simulation of microstrip phased array antenna for 2.0–2.8 GHz Handayani, Kurnia Wati Pascitra; Soim, Sopian; Anugraha, Nurhajar
Jurnal Teknika Vol 21, No 1 (2025): June 2025
Publisher : Faculty of Engineering, Universitas Sultan Ageng Tirtayasa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62870/tjst.v21i1.33816

Abstract

This study aims to create and test a microstrip array antenna with eight elements that works in the 2.0–2.8 GHz frequency range. We use CST Studio Suite to run simulations that check performance metrics like return loss (S11), VSWR, gain, and radiation pattern. The results show that the antenna has a return loss of -24 dB and a VSWR of 1.13 at a frequency of 2.4 GHz, which means the impedance is very well matched. However, the radiation and total efficiencies at 2 GHz and 2.8 GHz are still low, so the design can't handle the highest frequencies in the working range. The 126 MHz bandwidth should be able to cover channels 1 to 13 in Band 40 (2300–2400 MHz), but the antenna needs to work better at frequencies above 2.4 GHz to be helpful for all applications. Compared to other studies, this antenna's gain and efficiency are still not as good as those of other phased array antennas. This study is the first step towards creating a possible digital beam steering system that adaptively aligns signals to user movement to reduce interference in mobile environments.
Akselerasi Gerakan Maju Pada Robot Berkaki Empat Menggunakan Fuzzy Logic Soim, Sopian; Amperawan, Amperawan; Anisah, Masayu; Farhan, Novendra
Jurnal Ampere Vol. 7 No. 2 (2022): JURNAL AMPERE
Publisher : Universitas PGRI Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31851/ampere.v7i2.9503

Abstract

 This study designed a quadruped robot using a servo motor make movements while navigating. The quadruped robot was designed by controlling 128 rules on the Arduino Mega for movement using the AX12 servo motor, the navigating was evaluated by measured distance reading with the SharpGP sensor and movement acceleration using fuzzy method. This study was aimed to produce a quadruped robot which can be able to navigate using fuzzy method. The parameters used in this study are fuzzification, inference and defuzzification. Based on the quadruped robots in navigating, the success rate of reading 6 infrared sensors in detecting existing objects which ranged from 98 to 100% with an error rate of 1.07%. The accuracy of the success rate of the robot's forward movement speed, backward movement, swipe right and swipe left were at  100%, 40% , 60% and 40% respectivelyABSTRAKPada penelitian ini merancang  sebuah Robot berkaki  empat mengunakan motor servo  dalam  melakukan gerakan saat bernavigasi.  Robot berkaki empat  dirancang dengan pengendalian 128 rule pada  Arduino Mega untuk  gerakan menggunakan motor servo AX12, pembacaan jarak dengan sensor  SharpGP dan  akselarasi  gerakan menggunakan  metode fuzzy dalam melakukan  navigasinya. Penelitian ini  bertujuan membuat  robot berkaki empat dapat melakukan navigasi  dengan metode fuzzy. Data yang diambil pada saat bernavigasi berupa data fuzzifikasi, inferensi dan  defuzzifikasi. Berdasarkan  penelitian robot berkaki empat dalam bernavigasi  didapat  tingkat keberhasilan dari pembacaan 6 buah sensor infrared dalam mendeteksi objek yang ada berkisar 98% - 100%   dengan tingkat error sebesar 1.07%., akurasi tingkat keberhasilan kecepatan gerakan maju robot 100% , gerakan mundur 40%, gerakan geser kanan 60% dan 40% gerakan geser kiri. 
SELEKSI FITUR DENGAN GENETIKA ALGORITHM UNTUK OPTIMASI RANDOM FOREST DALAM MENGKLASIFIKASI TENTANG JENIS PENGGUNAAN INTERNET Rodicky, Nadio; Soim, Sopian; Zefi, Suzan
Transmisi: Jurnal Ilmiah Teknik Elektro Vol 27, No 3 Juli (2025): TRANSMISI: Jurnal Ilmiah Teknik Elektro
Publisher : Departemen Teknik Elektro, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/transmisi.27.3.185-190

Abstract

Penggunaan internet yang semakin meluas menimbulkan kebutuhan untuk memahami pola dan jenis aktivitas yang dilakukan pengguna. Klasifikasi jenis penggunaan internet dapat membantu dalam berbagai aplikasi, seperti manajemen jaringan, analisis web, dan pengembangan layanan internet yang lebih personal. Penelitian ini bertujuan untuk mengoptimalkan model klasifikasi jenis penggunaan internet menggunakan seleksi fitur dengan algoritma genetika dan Random Forest. Dataset yang digunakan dalam penelitian ini berisi informasi tentang lalu lintas internet, seperti alamat IP, nama domain yang dikunjungi, protokol yang digunakan, durasi kunjungan, dan jenis aktivitas. Algoritma genetika digunakan untuk menyeleksi subset fitur yang optimal untuk klasifikasi, sedangkan Random Forest digunakan sebagai algoritma klasifikasi. Hasil penelitian menunjukkan bahwa seleksi fitur dengan algoritma genetika dapat meningkatkan akurasi klasifikasi Random Forest secara signifikan. Penelitian ini memberikan kontribusi dalam pengembangan metode klasifikasi jenis penggunaan internet yang lebih akurat dan efisien. Hasil penelitian ini juga dapat digunakan sebagai dasar untuk penelitian selanjutnya dalam bidang analisis jaringan dan pengembangan layanan internet.
SOSIALISASI DAN SIMULASI KEAMANAN SERVER KERBEROS DAN OPENLDAP DI SMK NEGERI 4 PALEMBANG Lindawati; Fadhli, Mohammad; Soim, Sopian; Deta Mediana, Salwa
Aptekmas Jurnal Pengabdian pada Masyarakat Vol 7 No 3 (2024): Aptekmas Volume 7 Nomor 3 2024
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Computer networks are essential to daily life in the digital age because they link devices and provide distant information access. But technological progress also poses serious concerns to data security. Threats like viruses, malware, and hacker attacks put data's confidentiality and integrity in danger. For this reason, cybersecurity technicians must comprehend and use strong security frameworks. Kerberos, a security protocol that enables entities in a network to safely verify their identities, is one of the solutions that are presented. On the other side, directories are managed via Lightweight Directory Access Protocol (LDAP). In this context, teachers and students at the Vocational High School (SMK) with a focus on computer and network engineering receive instruction and training on network security. It is hoped that by doing this outreach, the community would see how important network security is and take the necessary precautions to safeguard data from intrusions. The outreach efforts were conducted at SMK Negeri 4 Palembang, which is the subject of this study. The findings demonstrate that students are able to test exploitation techniques on the framework used in the apache2 service and have a solid understanding of Kerberos, LDAP, and Firewalld.
Development of a Distributed Gradient Boosting Forest Algorithm with Residual Connections in Data Classification Respati, Rayhan Dhafir; Soim, Sopian; Fadhli, Mohammad
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.4899

Abstract

The growing complexity and volume of data across various domains necessitate machine learning models that are scalable and robust for large-scale classification tasks. Ensemble methods such as Gradient Boosting Decision Trees (GBDT) demonstrate effectiveness; however, they encounter issues concerning scalability and training stability when applied to very deep architectures. This work presents a novel enhancement using residual connections derived from deep neural networks into the Distributed Gradient Boosting Forest (DGBF) algorithm. By enabling direct gradient propagation across layers, residual connections solve the vanishing gradient problem and so improve gradient flow, accelerate convergence, and stabilise the training process. The Residual DGBF model was assessed using seven distinct datasets across the domains of cybersecurity, financial fraud, phishing, and malware detection. The Residual DGBF consistently surpassed the baseline DGBF in terms of accuracy, precision, recall, and F1-score across all datasets. Particularly in datasets marked by imbalanced classes and complex feature interactions, this suggests improved generalisation and higher predictive accuracy. By proving more stable and strong gradients across the depth of the model, layer-wise gradient magnitude analysis supports these improvements and so confirms the effectiveness of residual connections in deep ensemble learning. This work improves ensemble techniques by combining the scalability and interpretability of decision tree ensembles with the residual architecture optimising benefits. The proposed Residual DGBF enables future research on enhanced deep boosting frameworks by offering a strong and scalable method to address challenging real-world classification tasks.
Co-Authors Abu Hasan Ade Silvia Handayani Adewasti Adewasti Adewasti, Adewasti Ahmad Adriansyah Ahmad Jazuli Ahmad Taqwa Ali Nurdin Alpharisy, Kevin Farid Alqhaniyyu, Faris Amiza, Ibel Dwi Amperawan Amperawan Amperawan Amperawan, Amperawan Anisah, Masayu APRILIANI, DEFINA Aryanti Aryanti . Aryanti Aryanti Ciksadan, Ciksadan Damsi, Faisal Deta Mediana, Salwa Diraputra, M Yoga Azto Dody Novriansyah Fadhli, Mohammad Fahrudin, Gantar Fitra Faisal Damsi, Faisal Farhan, Novendra Fathria Nurul Fadillah Fatimatuzzahra Fatimatuzzahra Fistania Ade Putri Maharani Frenica, Agnes Garnis, Aishah Garnis, Aishah Gusni Amini Siagian Hafizh Ulwan Handayani, Kurnia Wati Pascitra Hj. Lindawati Humairoh, Sherina Husni, Nyayu Latifah Ihsan Mustaqiim Irawan Hadi Irawan Hadi Irma Salamah Irma Salamah Jami, Nurlita Joni, Bahri Joni, Bahri Junaidi Junaidi Junaidi Junaidi Junaidi, Junaidi Kgs Muhammad Farhan Rabbaniansyah Khairunnisa Khairunnisa L. Lindawati LINDAWATI Lindawati Lindawati Lindawati Lindawati Lindawati Lindawati M Yoga Azto Diraputra Maharani, Fistania Ade Putri Martinus Mujur Rose Mohammad Fadhli Muhammad Zakuan Agung Mujur Rose Nabila, Puspita Aliya Nadiah Nadiah Nakiatun Niswah Nasron Nasron Novianda, Nabila Rizqi Novianda, Nabila Rizqia Novriansyah, Dody Nurhajar Anugraha Nurul Fadhilah Oktariani Oktariani Oktariani, Oktariani Oktavia Manalu, Ria Pipit Wulandari Putri Andela Putri Vandalis, Yoke Annisa Putri, Alda Nabila Rabbaniansyah, Kgs Muhammad Farhan Raihanah, Adinda Ramadhan, Muhammad Fadli Rani Purnama Sari Repi, Intan Putri Ayu Agita Respati, Rayhan Dhafir Riona Alpeni Rivaldo Arviando Rizky, Putri Alifia Rodicky, Nadio Rose, Mujur Rumiasih Rumiasih Salsabila Dina Sari Sari, Rani Purnama Sarjana Sarjana Sarjana, Sarjana Savitri, Yulivia Rhadita Seliana, Imalda Septiani, Dinda Sholihin Sholihin Sholihin Sholihin Subianto, Cahyo Bayu Suci Lutfia Nisa Sudirman Yahya Suroso Suroso Suroso Suroso suzan zefi Tarnita Rizky Prihandhita Tely, Aristo Theresia Enim Agusdi Trisa Azahra Wulandari, Pipit Yanziah, Asma Zakuan Agung, Muhammad