Claim Missing Document
Check
Articles

Found 40 Documents
Search

Implementation of YOLOv8 for Object Detection in Urban Traffic Surveillance A Case Study on Vehicles and Pedestrians from CCTV Imagery Saragih, Rusmin; Imeldawaty Gultom; Frans Ikorasaki; Theodora MV Nainggolan
Journal of ICT Applications System Vol 4 No 1 (2025): Journal of ICT Aplications and System
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56313/jictas.v4i1.430

Abstract

Implementation of the YOLOv8 object detection algorithm for enhancing traffic surveillance through accurate identification of multiple road entities, including cars, motorcycles, trucks, and pedestrians. Using a 41-second CCTV video as the primary dataset, the research adopts a deep learning-based training approach via Google Colab to evaluate YOLOv8's performance under real-world urban conditions. The detection model was assessed using key evaluation metrics such as accuracy, precision, recall, and Mean Average Precision (mAP). The experimental results demonstrate that YOLOv8 achieves an overall detection accuracy of 80%, showing reliable performance in identifying vehicles and people despite challenges such as occlusions, varied lighting, and complex backgrounds. However, accuracy variations were observed in cases involving partial visibility and non-optimal camera angles. The findings highlight the potential of YOLOv8 as a robust and scalable solution for real-time traffic object detection, with implications for smart city development and automated traffic management systems. Further improvements are recommended in dataset diversity and model fine-tuning to enhance detection robustness across dynamic traffic scenarios
Penerapan Metode Apriori untuk Mengidentifikasi Korelasi Nilai Siswa di Sekolah Menengah Pertama Novita Anggraini; Relita Buaton; Imeldawaty Gultom
Jurnal ilmiah Sistem Informasi dan Ilmu Komputer Vol. 5 No. 3 (2025): November: Jurnal ilmiah Sistem Informasi dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juisik.v5i3.1443

Abstract

Currently, education is developing very rapidly, starting from the school level even up to the university level. Quality human resources depend on education. Student learning achievement which is usually indicated by report card grades is one of the benchmarks of educational success. However, student grade data for strategic decision making in schools is often done manually and is not optimal. This study aims to identify correlations between student grades in Junior High Schools and apply the Apriori method in data analysis to determine the relationship between student grades and other variables such as subjects and achievement levels. This study involved data collection consisting of 508 students. The Apriori method successfully identified relevant correlations, such as students in Pancasila Education subjects received a B, ICT received a B, Mathematics received a B, English received a B, Social Studies received a B, Craft received a B, Indonesian received a B, Physical Education received a B, Science received a B, SBK received a B, Religious Education received a B, then the Achievement Level is Low with support 3.90% and confidence 95.20%. The use of RapidMiner software in data analysis provides recommendations for robust relationships or correlations. This research is expected to provide sound recommendations to support the achievement of national education goals by identifying the relationship between student grades and subject matter, as well as improving learning outcomes based on student achievement levels.
Pelatihan Peningkatan Kompetensi Guru dalam Penggunaan Canva untuk Pembelajaran Berdiferensiasi pada Kurikulum Merdeka Gultom, Imeldawaty; Saragih, Rusmin; Pakpahan, Emma Martina
Pengabdian Pendidikan Indonesia Vol. 2 No. 01 (2024): Artikel Periode April 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/ppi.v2i01.4528

Abstract

Pelatihan peningkatan kompetensi guru dalam penggunaan Canva untuk pembelajaran berdiferensiasi di SMP Swasta Primbana Medan bertujuan untuk memperkuat keterampilan guru dalam memanfaatkan teknologi untuk mendukung implementasi Kurikulum Merdeka. Kegiatan ini berangkat dari kebutuhan untuk meningkatkan kualitas materi pembelajaran dan keterlibatan siswa melalui penggunaan alat digital yang inovatif. Pelatihan ini melibatkan sesi teori dan praktik yang dirancang untuk mengenalkan fitur Canva dan aplikasinya dalam pembuatan materi ajar yang visual dan interaktif. Metodologi yang digunakan dalam pelatihan ini mencakup pendekatan kualitatif dan kuantitatif. Data dikumpulkan melalui wawancara, kuesioner, observasi, dan analisis dokumen untuk menilai peningkatan keterampilan guru dan kualitas materi pembelajaran yang dihasilkan. Hasil dari pelatihan menunjukkan peningkatan signifikan dalam keterampilan guru dalam menggunakan Canva, yang berdampak positif pada kualitas materi pembelajaran. Guru-guru di SMP Swasta Primbana Medan kini dapat menciptakan materi yang lebih menarik dan sesuai dengan kebutuhan siswa, yang pada gilirannya meningkatkan keterlibatan dan motivasi siswa. Pelatihan ini juga berhasil membentuk komunitas belajar di kalangan guru, di mana mereka saling berbagi pengetahuan dan pengalaman dalam penggunaan Canva. Temuan ini menunjukkan bahwa integrasi teknologi seperti Canva dapat mendukung pembelajaran berdiferensiasi dan pelaksanaan Kurikulum Merdeka dengan lebih efektif. Rencana tindak lanjut meliputi pendampingan berkelanjutan dan pengembangan modul pelatihan tambahan untuk memperkuat kemampuan guru dalam memanfaatkan teknologi pendidikan.
Visualization and Analysis of Employee Performance Data Using a Power BI-based Business Intelligence Dashboard Imeldawaty Gultom; Eka Pandu Cynthia; Chinthia, Maulidania Mediawati
Journal of Computer Science, Artificial Intelligence and Communications Vol 1 No 2 (2024): November 2024
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v1i2.19

Abstract

In the current digital and competitive era, the utilization of Business Intelligence (BI) technology has become crucial in supporting data-driven decision-making. This research aims to develop and analyze a Power BI-based Business Intelligence dashboard focused on visualizing employee performance. This study was conducted by collecting performance data from the Human Resource Information System (HRIS), which was then processed and visualized in the form of key metrics such as attendance rates, individual target achievements, productivity per division, and periodic performance evaluations. Power BI was chosen for its ability to integrate various data sources and present interactive visualizations that are easy for management to understand. The methodology used involves the ETL (Extract, Transform, Load) process, data model design, and the development of visual reports that support descriptive and comparative analysis. The results of this study indicate that the use of BI dashboards significantly helps the company in monitoring employee performance in real-time, identifying trends in productivity decline, and designing data-driven improvement strategies. In addition, this dashboard also serves as an effective communication tool between management and the HR division. Thus, the use of Power BI as a tool for visualization and performance analysis adds significant value to the strategic and data-driven management of human resources
Penerapan Algortima K-Means untuk Mengelompokkan Siswa Berdasarkan Tingkat Pemahaman dan Kemandirian Belajar dalam Kurikulum Merdeka Ingke Fuji Utami Br Barus; Novriyenni Novriyenni; Imeldawaty Gultom
Merkurius : Jurnal Riset Sistem Informasi dan Teknik Informatika Vol. 3 No. 6 (2025): November: Merkurius: Jurnal Riset Sistem Informasi dan Teknik Informatika
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/merkurius.v3i6.1141

Abstract

The Merdeka Curriculum implemented in various schools in Indonesia aims to provide flexibility in learning, where students can learn according to their individual needs, interests, and pace. One of the challenges in implementing this curriculum is how to effectively identify classroom activity and student discipline. SD Islamiyah, as a school that implements the Merdeka Curriculum, also faces challenges in understanding variations in student classroom activity and discipline. Some students are able to learn in a disciplined manner with little guidance, while others require more intensive support from teachers. Therefore, a system is needed that can group student data more systematically so that teachers can develop teaching strategies that suit the needs of each group of students. One algorithm that can be used in data grouping is k-means clustering. The K-Means algorithm is a non-hierarchical algorithm derived from the data clustering method. The K-Means algorithm begins with the formation of cluster partitions at the beginning, then iteratively refines these cluster partitions until there are no significant changes in the cluster partitions. The K-Means method partitions data into groups so that data with similar characteristics are placed in the same group and data with different characteristics are grouped into other groups. This method can help group students more accurately based on their Class Activity and Discipline. From the results of the analysis, it was concluded that the student data group with Class Activity was Moderately Active Students, with Discipline being Disciplined, and an average score of 71-80.
The Effect of Social Media on Student Learning Motivation Using the Apriori Method Tiwi, Chairmayni Pratiwi; Maulita, Yani; Gultom, Imeldawaty
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 3 No. 1 (2023): October 2023
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v3i1.273

Abstract

The success of student learning can be determined by their motivation. Students who have high learning motivation tend to have high achievement as well, otherwise their learning motivation is low, their learning achievement will also be low. student learning motivation in the subject is very low. Some students prefer to play social media rather than pay attention to the material explained by the teacher during class hours. Therefore, this study aims to explore the influence of social media on students' learning motivation. This research uses data mining method with Apriori algorithm to identify patterns related to social media usage and students' learning motivation. The Apriori algorithm is one of many algorithms in data mining that is used for frequent itemsets and association rules in databases on transactional data that are generated by identifying each item that exists, and combining larger sets of items provided that the items appear frequently enough in the database. Based on the research that has been done, the author can draw the conclusion that using the Rapid Miner 7.1 application tools in applying the apriori algorithm produces the same rules as manual calculations using 300 data on the learning motivation of Abdi Negara Binjai SMKS students and the system can generate association rules using 300 student learning motivation data with a minimum support of 12% and a minimum confidence of 75% and produce 5 association rules 3 itemsets to determine the learning motivation of Abdi Negara Binjai SMKS students. One of the rules that has the highest confidence value is, if YT and J2 then M1. Which means that every student who uses YOUTUBE Social Media with a length of use is 3-4 HOURS then INCREASES STUDY MOTIVATION. Then the less the ɸ (frequent) value is set, the more data that can be processed, as well as the minimum support value and confidence value, where the smaller the value determined, the more association results will be issued.
Pemanfaatan Aplikasi Kasir Digital Berbasis Android untuk UMKM di Desa Cinta Rakyat Saragih, Rusmin; Gultom, Imeldawaty; Supiyandi; Khalidy, Furqan
Jurnal Pengabdian Masyarakat Berdampak Vol. 1 No. 1 (2025): Januari 2025
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jupemba.v1i1.34

Abstract

Pemanfaatan teknologi digital dalam pengelolaan usaha mikro, kecil, dan menengah (UMKM) menjadi strategi penting untuk meningkatkan efisiensi operasional dan daya saing. Penelitian ini bertujuan untuk mengkaji implementasi aplikasi kasir digital berbasis Android dalam mendukung aktivitas transaksi dan pencatatan keuangan UMKM di Desa Cinta Rakyat. Metode yang digunakan adalah pendekatan deskriptif kualitatif melalui observasi, wawancara, dan pelatihan langsung kepada pelaku UMKM. Hasil kegiatan menunjukkan bahwa mayoritas pelaku UMKM sebelumnya masih menggunakan pencatatan manual yang rentan terhadap kesalahan dan kehilangan data. Dengan diperkenalkannya aplikasi kasir digital seperti Kasir Pintar dan Moka POS, pelaku usaha dapat mencatat transaksi secara real-time, memantau stok barang, serta menghasilkan laporan keuangan sederhana. Selain itu, penggunaan aplikasi ini meningkatkan pemahaman pelaku UMKM terhadap pentingnya digitalisasi dalam manajemen usaha. Kendala yang ditemui mencakup keterbatasan literasi digital dan akses terhadap perangkat yang memadai, namun dapat diatasi melalui pelatihan berkelanjutan dan pendampingan teknis. Penelitian ini menyimpulkan bahwa aplikasi kasir digital berbasis Android berperan signifikan dalam mendukung tata kelola keuangan UMKM secara lebih akurat dan efisien. Rekomendasi diarahkan pada perlunya dukungan dari pemerintah desa dan pihak terkait untuk menyediakan infrastruktur pendukung dan memperluas program literasi digital guna mempercepat adopsi teknologi oleh pelaku UMKM di pedesaan.
Design and Techno Economic Performance Assessment of Hydrogen Based Hybrid Microgrid Systems for Sustainable Industrial Energy Management Imeldawaty Gultom; Wibisono Wibisono; Sigit Wibisono; Aji Nurohman; Irlon Irlon
International Journal of Mechanical, Industrial and Control Systems Engineering Vol. 1 No. 1 (2024): March: IJMICSE: International Journal of Mechanical, Industrial and Control Sys
Publisher : Asosiasi Riset Ilmu Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/ijmicse.v1i1.401

Abstract

Hydrogen-based hybrid microgrid systems have emerged as a promising solution to enhance renewable energy integration and improve energy supply reliability. By combining renewable sources such as solar and wind with hydrogen production and storage technologies, these systems address the intermittency of renewable power while ensuring continuous energy availability. This study evaluates the techno-economic feasibility, environmental impact, and scalability of hydrogen-based hybrid microgrids, with a focus on cost-effectiveness and system performance under varying operating conditions. Simulation tools, including HOMER Pro and MATLAB Simulink, are used to model the system and conduct sensitivity analyses on hydrogen production costs and demand fluctuations. Key performance indicators such as Levelized Cost of Energy (LCOE), Net Present Value (NPV), and CO₂ emissions reduction are assessed. The results show that although the system requires a high initial investment, it becomes economically viable over time due to reduced operational costs and improved efficiency. Additionally, the system demonstrates significant environmental benefits, outperforming conventional fossil fuel-based systems in terms of emissions reduction. Sensitivity analysis further indicates that advancements in hydrogen production technologies could substantially enhance economic feasibility. Overall, hydrogen-based hybrid microgrids offer a reliable and low-carbon energy solution, supporting sustainable energy transitions and reducing dependence on fossil fuels.
Design Of Automatic Hand Sanitizer Spray System Based On Arduino Uno Using Fuzzy Logic Method Firhan Ali; Husnul Khair; Imeldawaty Gultom
International Journal of Health Engineering and Technology Vol. 3 No. 4 (2024): IJHET NOVEMBER 2024
Publisher : CV. AFDIFAL MAJU BERKAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1045.192 KB) | DOI: 10.55227/ijhet.v1i2.32

Abstract

Washing hands is the act of cleaning like fingers to wrists using water or other liquids. Hand sanitizer with a minimum alcohol content of 60% is believed to be effective for killing germs and other harmful microorganisms because hands are one part of the body that often interacts such as touching and can be a medium for the spread of viruses, germs and bacteria. The manufacture of tools is carried out as one of the efforts in advancing technology to provide convenience and comfort through the development of an automatic system for hand sanitizer containers. From the above problems an Arduino based automatic hand sanitizer system was created. This system works directly to be able to spray liquid automatically. This system is expected to make it easier for users to spray liquids without having to do it manually or touching the container directly to maximize time efficiency and keep it clean. By designing a prototype to make this automatic hand sanitizer using an ultrasonic sensor as input, Arduino Uno Atmega328p as a microcontroller, and a servo motor as a driver for the hand sanitizer container. The system on the tool to be made is capable of spraying liquid automatically at a maximum distance of 10 centimeters.
Aplikasi Pemesanan Perjalanan Paket Wisata Religi Pada PT. Vakansi Mandala Nusantara Berbasis Android Disnu Panggabean; satria SI; Yunita Dana Br Purba; Imeldawaty Gultom
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 2 No. 1 (2023): Juni 2023
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v2i1.77

Abstract

Perkembangan suatu sistem yang semakin lama semakin marak memungkinkan masyarakat untuk mencari inovasi baru dalam mempermudah suatu kegiatan yang ingin dilakukan. Telah banyak paket wisata yang memberikan opsi perjalanan yang menarik namun banyak nya data dan tingkat kerumitan dalam proses pemesanan sehingga mumbutuhkan waktu yang banyak untuk melakukan pembelian tiket wisata dan juga sulit diketahui oleh kalangan masyarakat karena kurangnya suatu ketersediaan media promosi yang menampilkan informasi yang lebih detail dan terupdate. Adanya perkembangan sistem memberikan hak akses kepada masyarakat untuk dapat menerima informasi terupdate yang telah dipaparkan secara lebih detail sehingga memicu minat masyarakat dalam menggunakan suatu aplikasi terbaru seperti aplikasi pemesanan paket perjalanan wisata berbasis android. PT.Vakansi Mandala Nusantara kini telah mengembangkan suatu sistem android yang lebih fleksibel yang dapat diakses dimana saja dan kapan saja karena telah memberikan kemudahan bagi para penggunanya dalam menikmati ketersediaan paket perjalanan wisata yang membantu masyarakat dalam melakukan transaksi serta melakukan suatu proses pemesanaan. Metode yang digunakan dalam penelitian ini adalah metode prototype, metode ini telah berhasil mengembangkan suatu sistem yang dimana pelanggan dapat saling melakukan interaksi sehingga pelanggan ataupun pemilik sistem mempunyai gambaran jelas pada sistem terpadu yang telah disediakan. Pada metode ini dibangun aplikasi berbasis android ini betujuan untuk mengurangi suatu resiko kesalahan pada saat pengelolaan data dan meminimalkan waktu yang telah terbuang karena awalnya proses transaksi dan pemilihan paket perjalanan wisata dilakukan secara manual.