Claim Missing Document
Check
Articles

Implementasi Dan Pengembangan Dashboard Akademik Feeder PDDikti Dengan Data Mart: Studi Kasus Universitas Dinamika Bangsa Rahim, Abdul; Wardani, Muhammad; Alam Jusia, Pareza; Siswanto, Agus
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 5 No 1 (2025): JAKAKOM Vol 5 No 1 APRIL 2025
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2025.5.1.2184

Abstract

Reporting academic data to the Pangkalan Data Pendidikan Tinggi (PDDIKTI) is a mandatory requirement for higher education institutions to ensure the validity and synchronization of student, lecturer, course, and academic activity data. However, in practice, several challenges arise, such as discrepancies between the internal academic system (Siakad) and the Feeder PDDIKTI, delays in reporting, and difficulties in monitoring synchronization status in real-time. This study aims to develop an academic data reporting monitoring dashboard based on a Data Mart, enabling efficient and centralized monitoring of academic data synchronization. The dashboard integrates data from Feeder PDDIKTI and Siakad through the Extract, Transform, Load (ETL) process to generate accurate and easily interpretable information. The findings indicate that the developed dashboard effectively visualizes academic data synchronization status in real-time, reduces reporting errors, and accelerates the validation process before submission to PDDIKTI. Thus, this dashboard serves as an effective solution to support academic data governance in higher education institutions
Analisis Kandungan Nutrisi Berbagai Jenis Makanan Menggunakan Visualisasi Dashboard Interaktif Pada Database USDA : Utilization of Dashboards to Facilitate Nutritional Analysis of Various Food Types Yafi, Zidni Reynard; Rahim, Abdul; Siswanto, Agus
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 5 No 1 (2025): JAKAKOM Vol 5 No 1 APRIL 2025
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2025.5.1.2278

Abstract

In today's modern era, awareness of the importance of a healthy diet and balanced nutritional consumption is increasing. However, people are still faced with the problem of a lack of understanding of the nutritional content of various types of food consumed daily. Therefore, an in-depth analysis of the nutritional content of food is an important step to provide accurate information that can be used by individuals, nutritionists, and the food industry. Information about this content can help individuals and institutions, such as nutritionists and the food industry. Nutrition in food plays an important role in maintaining health, this project aims to analyze the nutritional content of various types of food using the USDA (United States Department of Agriculture) database as the main data source. The data is then visualized in the form of an interactive dashboard to facilitate interpretation of the information. In the analysis process, the data is cleaned and processed using structured data management techniques. The results of this analysis are in the form of visualizations that display comparisons of nutritional content between food groups and understand nutritional patterns in more depth.
Enhancing Areca Nut Detection and Classification Using Faster R-CNN: Addressing Dataset Limitations with Haar-like Features, Integral Image, and Anchor Box Optimization Pratama, Yovi; Rasywir, Errissya; Suyanti; Siswanto, Agus; Fachruddin
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 3 (2025): June 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i3.6496

Abstract

The classification and detection of areca nuts are essential for agriculture and food processing to ensure product quality and efficiency. The manual classification of areca nuts is time-consuming and prone to human error. For a more accurate and efficient automated approach, a deep learning-based framework was proposed to address these challenges. This study optimizes the Faster R-CNN by integrating Haar-like features and integral images to enhance object detection. However, dataset limitations, including low image quality, inconsistent lighting, cluttered backgrounds, and annotation inaccuracies, affect the model performance. In addition, the small dataset size and class imbalance hindered generalization. The Faster R-CNN model was trained with and without Haar-like Features and Integral Image enhancement. Performance was evaluated based on training loss, accuracy, precision, recall, F1-score, and mean average precision (mAP). The effects of the dataset limitations on detection performance were also analyzed. The optimized model achieved better stability, with a final training loss of 0.2201, compared to 0.1101 in the baseline model. Accuracy improved from 62.60% to 73.60%, precision from 0.6161 to 0.7261, recall from 0.3094 to 0.4194, F1-score from 0.2307 to 0.3407, and mAP from 0.1168 to 0.2268. Despite these improvements, dataset constraints remain a limiting factor. While the integration of Haar-like features and integral images into faster R-CNN contributes to detection accuracy, the study also reveals that high-resolution images, precise annotations, and dataset scale significantly amplify model performance.
PELATIHAN A.I PROMPTING UNTUK PENINGKATAN KEMAMPUAN BELAJAR MANDIRI PADA SISWA-SISWI SMA NEGERI 4 MUARO JAMBI Pebrianto, Feri; Beny; Yani, Herti; Rahim, Abdul; Siswanto, Agus; Alam Jusia, Pareza; Paramitha, Cindy
Jurnal Pengabdian Masyarakat UNAMA Vol 4 No 1 (2025): JPMU Volume 4 Nomor 1 April 2025
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jpmu.2025.4.1.2157

Abstract

Pelatihan kecerdasan buatan (AI) memiliki potensi besar dalam mendukung pembelajaran mandiri di kalangan siswa – siswi. Kegiatan Pengabdian Kepada Masyarakat (PKM) berupa "Pelatihan AI Prompting untuk Peningkatan Kemampuan Belajar Mandiri pada Siswa-Siswi SMA Negeri 4 Muaro Jambi." Kegiatan ini bertujuan untuk memperkenalkan aplikasi AI serta memberikan keterampilan kepada siswa dalam merancang instruksi atau "prompt" yang jelas dan efektif untuk berinteraksi dengan AI, seperti ChatGPT dan Gemini AI. Dengan pelatihan ini, diharapkan siswa mampu memanfaatkan AI sebagai alat bantu dalam proses belajar, meningkatkan kemampuan belajar mandiri, dan memperluas akses mereka terhadap informasi yang relevan. Kegiatan ini direncanakan berlangsung selama enam bulan dengan target siswa SMA Negeri 4 Muaro Jambi, serta hasil luaran berupa peningkatan pemahaman siswa tentang AI.
Flower Polination Algorithm Sebagai Optimalisasi LFC Pada Hybrid Pembangkit Wind-Diesel Ali, Machrus; Siswanto, Agus; Baehaqi, Mudofar
Jurnal FORTECH Vol. 5 No. 1 (2024): Jurnal FORTECH
Publisher : FORTEI (Forum Pendidikan Tinggi Teknik Elektro Indonesia)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56795/fortech.v5i1.5106

Abstract

As input power, the amount of wind and wind speed greatly influences the wind power generation system. A combination of a wind-diesel power generation system is needed to obtain optimal power quality. A hybrid system is a controlled network of multiple renewable energy generators such as wind turbines, solar cells, micro-hydro, and so on. Gain settings that are not optimal and the time constant is small in Load Frequency Control (LFC), causing its ability to be weak (weak line). In practice, the wind-diesel system is controlled with a PID controller. Setting the gain value of the PID is still in the conventional method, so it is difficult to get the optimal value. In this research, a control design was implemented using the Smart Method to find the optimum value of the Proportional Integral Derivative (PID) based on the FPA (Flower Pollination Algorithm). For comparison, methods were used without control methods, conventional PID methods, PID Auto tuning methods, and FPA (Flower Pollination Algorithm) methods. Wind-diesel modeling uses transfer function diagrams of wind and diesel turbines. This study compares several uncontrolled methods and conventional PID, PID-Auto tuning, and PID-FPA. The results of the research that has been carried out show that the smallest undershoot is -1.187.10-04 for PID-FPA, the smallest overshot is 0 for PID-FPA, and the fastest settling time is 9.827 s for PID-FPA. So it can be concluded that PID-FPA is the best controller in this research. This research can later be continued using other artificial intelligence methods.
Comparison of robust machine learning algorithms on outliers and imbalanced spam data Abidin, Dodo Zaenal; Jasmir, Jasmir; Rasywir, Errisya; Siswanto, Agus
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 2: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i2.pp1130-1144

Abstract

Effective spam detection is essential for data security, user experience, and organizational trust. However, outliers and class imbalance can impact machine learning models for spam classification. Previous studies focused on feature selection and ensemble learning but have not explicitly examined their combined effects. This study evaluates the performance of random forest (RF), gradient boosting (GB), and extreme gradient boosting (XGBoost) under four experimental scenarios: (i) without synthetic minority over-sampling technique (SMOTE) and outliers, (ii) without SMOTE but with outliers, (iii) with SMOTE and without outliers, and (iv) with SMOTE and with outliers. Results show that XGBoost achieves the highest accuracy (96%), an area under the curve-receiver operating characteristic (AUCROC) of 0.9928, and the fastest computation time (0.6184 seconds) under the SMOTE and outlier-free scenario. Additionally, RF attained an AUCROC of 0.9920, while GB achieved 0.9876 but required more processing time. These findings emphasize the need to address class imbalance and outliers in spam detection models. This study contributes to developing more robust spam filtering techniques and provides a benchmark for future improvements. By systematically evaluating these factors, it lays a foundation for designing more effective spam detection frameworks adaptable to real-world imbalanced and noisy data conditions.
Modification of Dynamic Voltage Restorer for Improved Power Quality in Industrial Electrical Networks Rosyadi, Marwan; Siswanto, Agus
Mestro: Jurnal Teknik Mesin dan Elektro Vol 7 No 1 (2025): Edisi Juni
Publisher : Fakultas Teknik Universitas 17 Agustus 1945 Cirebon

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47685/mestro.v7i1.683

Abstract

Reliable power quality is a crucial factor in maintaining continuity and operational efficiency in industrial power grids. Power quality disturbances such as voltage sags, voltage swells, and interruptions can cause equipment damage, decreased productivity, and increased operational costs. Dynamic Voltage Restorers (DVRs) have proven effective in addressing voltage disturbances, but conventional devices have limitations, specifically, they are only able to compensate for voltage drops up to approximately 30% of the nominal value and cannot address interruption disturbances. This study proposes a modified DVR with the addition of an energy storage system and an adaptive control algorithm to expand the voltage compensation capabilities, including under extreme voltage sags and interruption disturbances. Simulation results show that the modified DVR is able to maintain load voltages close to the nominal value under various disturbance scenarios, thereby significantly improving the power quality and reliability of the industrial power grid.
Analysis of Ethical Behavior, Perceive Organizational Support, Job Satisfaction, and Organizational Commitment on Employee Performance at PT Kilang Pertamina International, Cilacap, Central Java, Indonesia Sofiansyah, Muhammad Edi; Siswanto, Agus; Sutanto , Aftoni
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 4 No. 3 (2025): Agustus - October
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v4i3.2823

Abstract

This study aims to examine the influence of ethical behavior, organizational support, job satisfaction, and organizational commitment on employee performance at PT Kilang Pertamina International, Cilacap Unit. The research highlights how individual and organizational factors interact to shape work performance within the context of a strategic energy industry. A total of 270 respondents, selected through purposive sampling with a minimum of two years of tenure, participated in the survey. Data were analyzed using the Partial Least Squares–Structural Equation Modeling (PLS-SEM) approach with version 4.0, allowing for a rigorous assessment of both measurement validity and structural relationships among the constructs. The results indicate that all indicators demonstrate loading factors above 0.70, while the Average Variance Extracted (AVE) values range from 0.55 to 0.73, confirming the convergent validity of the constructs. In addition, the Composite Reliability (CR) values exceed 0.80, suggesting a high level of instrument reliability. The structural analysis further reveals that ethical behavior, organizational support, job satisfaction, and organizational commitment each exert a significant influence on employee performance. These findings not only reinforce prior literature concerning the role of behavioral and organizational factors in enhancing performance, but also provide practical implications for human resource management in the energy sector. Specifically, the study underscores the importance of fostering ethical practices, strengthening organizational support, and cultivating satisfaction and commitment as integral strategies for sustaining high levels of employee performance.
Peran Trust in Leader dalam Memediasi Pengaruh Servant Leadership terhadap Keterlibatan Kerja Aldiansyah, m.; Siswanto, Agus; Sutanto, Aftoni; Wibowo, Indi Deli Fiallo
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 4 No. 3 (2025): Agustus - October
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v4i3.2951

Abstract

Penelitian ini bertujuan untuk menganalisis pengaruh servant leadership terhadap keterlibatan kerja karyawan dengan trust in leader sebagai variable mediasi pada Kantor Lazismu wilayah DIY dan kota Yogyakarta. Penelitian dilatar belakangi oleh rendahnya tingkat keterlibatan kerja karyawan di Indonesia serta pentingnya gaya kepemimpinan yang berorientasi pada pelayanan dalam meningkatkan motivasi dan kesejahteraan kerja. Fokus penelitian ini adalah bagaimana gaya kepemimpinan yang melayani mampu membangun kepercayaan karyawan kepada pemimpin.Gaya kepemimpinan yang melayani dianggap penting karena menekankan empati, perhatian terhadap bawahan, dan tanggung jawab moral pemimpin dalam melayani kebutuhan karyawannya. Penelitian ini menggunakan metode kuantitatif dengan teknik sampling berupa sample jenuh. Sample yang digunakan dalam penelitian ini yaitu 54 karyawan dijadikan responden. Data yang digunakan dalam penelitian ini yaitu data primer yang diperoleh melalui kuesioner berbasis skala likert lima poin. Analisis dilakukan dengan metode Structural Equation Modeling (SEM) menggunakan perangkat lunak SmartPLS 3.  Hasil penelitian menunjukan bahwa servant leadership berpengaruh positif dan signifikan terhadap keterlibatan kerja selanjutnya servant leadership berpengaruh positif dan signifikan terhadap trust in leader, dan juga trust in leader berpengaruh positif dan signifikan terhadap keterlibatan kerja serta trust in leader memediasi secara positif dan signifikan hubungan antara servant leadership dan keterlibatan kerja. Temuan ini menunjukkan bahwa dalam organisasi non-profit seperti Lazismu, hubungan berbasis kepercayaan merupakan hal yang penting dan perlu diperhatikan.
Analysis of Lightning Disruption Reduction in HVAD Tower 70 kV Parallel Inductance Grounding using NA2XSY Cable in West Java Siswanto, Agus; Mucharomah, Nurul Maghfiroh; Ashad, Bayu Adrian; Rahman, Yuli Asmi
INTEK: Jurnal Penelitian Vol 7 No 1 (2020): In Press
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1305.294 KB) | DOI: 10.31963/intek.v7i1.2092

Abstract

The Sumadra - Pameungpeuk region has an uneven geographical location because it is traversed by mountains and beaches and has a high level of ISO Keraunic which causes many lightning strikes to occur in this region. The disturbance caused by lightning strikes is very worrying because it can disrupt the stability of electric power in West Java, Integrated Service Unit (ISU) Cirebon region in particular and can harm consumers as users of electricity. To minimize the disruption caused by lightning strikes in this study using the parallel mounting inductance method using NA2XSY cable. This study aims if there is a lightning strike on the GSW wire it can be immediately properly grounded. NA2XSY cable was chosen as direct grounding because the inductance value on the cable is smaller than the inductance value on the tower so that when NA2XSY cable is paralleled with the body tower it produces a low parallel inductance value so that it is expected to minimize the occurrence of back flashover due to the induction voltage resulting in the flash isolator. The results showed the lowest tower resistance value in the Sumadra-Pameungpeuk region of 0.21 ohms is located at tower number 77 and the highest resistance is 4.3 ohms at tower numbers 49 feet A and D, this meets PLN's standard of <5 ohms. Parallel inductance installation succeeded in reducing the disturbances caused by lightning, namely, in January-July 2018 the disruption occurred 4 times and in January - July 2019 became 2 times the disturbance.
Co-Authors Abdul Choliq Hidayat Abdul Manan Abdul Rahim Abdul Rosyid Abidin, Dodo Zaenal Achmad Fudholi ACHMAD FUDHOLI Achmad Fudholi Adithya Wahyu Pratama, Adithya Wahyu Aftoni Sutanto Ahmad Husain Asdie Akhir Riana Handayani, Akhir Riana Akhmad Kharis Nugroho Albait, Nur Aldiansyah, m. Amrullah, Bagaskara Falah Anjar Mahardian Kusuma Arvita, Yulia Ashad, Bayu Adrian Baedhowi, Abdul Latif Baehaqi, Mudofar Beny Dodit Ari Wibowo, Dodit Ari Dwi Hartanti Dwi Rahayuningsih E. Mudjaddid A. Siswanto Deddy N.W.Achadiono Hamzah Shatri Emelia, Shinta Endang Prihastuty, Endang Erfan Subiyanta, Erfan Errissya Rasywir eva rosmawati Eva Rosmawati Evi Sofia Fachruddin Fatimah Malini Lubis Fauziati, Ana Feranika, Ayu Feriyadin, Feriyadin Fiastuti Witjaksono Gustina Nurkhayatun, Gustina Hady, Sultan Hariadi Hariawan Hermawan, M. Reza Herti Yani, Herti Hery Sonawan Hidayat, Abdul Choliq Imam Baihaqi Imam Subekti Indri Hapsari Indri Hapsari Iskandar Soedirman, Iskandar Iskandar Sudirman Jasmir, Jasmir Junial Heri Kuntjoro Harimurti Machrus Ali Megantara, Marcelino A. Moeslich Hasanmihardja Mucharomah, Nurul Maghfiroh MUHAMMAD FURQONI Mutiara Poetri Nurtanti, Mutiara Poetri Nasrun, Martina W. Nunuk Aries Nurulita PAMUSO, MARLIN Paramitha, Cindy Pareza Alam Jusia, Pareza Alam Pebrianto, Feri Prayogo, Lito Pri Iswati Utami Purnomo, Luthfan Budi Rasywir, Errisya Reza Pramitha Habsari, Reza Pramitha Rizana Fauzi, Rizana Rizki Okprastowo rohadin, rohadin Rosalina, Mia Rosario, Maria rosmawati, eva Rosyadi, Marwan RR. Ella Evrita Hestiandari Rudi Putranto Rustiawan, Indra S.Kom.,M.Pd, Arifudin Setiawan, Zunan Siregar, Arief Kurniawan Siti Helmyati Siti Setiati Sofiansyah, Muhammad Edi Sudibyo Martono SUDIBYO MARTONO Sudibyo Martono Suhendro Suwarto, Suhendro Suparman Suparman Suparman Suparman Suryadi, Dikky Sutanto , Aftoni Sutoyo, Mochammad Arief Hermawan Suyanti Suyanti Suyanti Suzanna Immanuel Tohasan, Achmad W. Djoko Yudisworo Wachyu Hari Haji Wardani, Muhammad Wasiran, Wasiran Wibawa, Arief Wibowo, Indi Deli Fiallo Widya Cahya Ariswati, Widya Cahya Yafi, Zidni Reynard Yekti Mulyani, Yekti Yovi Pratama Yuli Asmi Rahman Yuni Ernawati, Yuni yusni ulfiani zulaikha Yusni Ulfiani Zulaikha zulaikha, yusni ulfiani