cover
Contact Name
Jumadi
Contact Email
indexsasi@apji.org
Phone
+6281578146104
Journal Mail Official
indexsasi@apji.org
Editorial Address
Perum. Bumi Pucanggading, Jln. Watunganten 1 No 1-6, Kelurahan Batursari, Mranggen , Kab. Demak, Provinsi Jawa Tengah, 59567
Location
Kab. demak,
Jawa tengah
INDONESIA
Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer
ISSN : 28090802     EISSN : 28090799     DOI : 10.51903
Core Subject : Engineering,
Jurnal Imliah Teknik Mesin, Elektro dan Komputer merupakan jurnal ilmiah yang menyajikan artikel orisinal tentang pengetahuan dan informasi riset atau aplikasi riset dan pengembangan terkini dalam bidang teknologi. Ruang lingkup Jurnal Juritek meliputi bidang Informatika, Teknik Mesin, Teknik Elektro, Sistem Informasi dan Teknik Industri. Artikel yang masuk akan melalui proses seleksi mitra bestari dan/atau editor. Jurnal Juritek diterbitkan oleh Lembaga Pengembangan Kinerja Dosen terbit 3 kali dalam setahun, yaitu pada bulan Maret, Juli dan November
Articles 304 Documents
Perancangan Sistem Informasi Manajemen Jam Ganti Guru Menggunakan Round Robin Berbasis Web: Studi Kasus: SMK Parulian 2 Medan Tri Yulistiani Siregar; Niko Surya Atmaja; Sahyunan Harahap
Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer Vol. 6 No. 2 (2026): Juli: Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

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

Abstract

SMK Parulian 2 Medan is a vocational school with 20 teachers managing 6 classes and a total of 180 teaching hours per week. The management of teacher substitution hours is currently still carried out based on direct considerations without using a structured mechanism. This condition gives rise to several problems, namely poorly organized teacher schedule data, the process of determining substitute teachers that takes quite a long time so that it can disrupt teaching and learning activities, and the distribution of substitute hours that is not evenly distributed among teachers. This study aims to design a web-based application for managing teacher substitution hours that is able to organize data in a structured manner, implement fair rotations in the assignment of substitute teachers, and present schedule information that is easily accessible. The proposed method is the Round Robin algorithm, which distributes substitute hour assignments in turns based on a certain order so that each teacher has an equal opportunity to receive additional teaching assignments. The resulting design allows for structured storage of teacher and schedule data in a database, automation of substitute teacher determination using the Round Robin mechanism, and presentation of information through a web-based interface that can be accessed by school administration staff. Compared to the current management method, the design offers more organized data management, faster replacement teacher assignments, and a more balanced distribution of teaching loads. This study concludes that web-based replacement teacher management integrated with the Round Robin algorithm can effectively address scheduling issues at SMK Parulian 2 Medan and improve the continuity of teaching and learning activities
Penerapan Algoritma Naive Bayes untuk Prediksi Potensi Hujan di Bandar Udara Tunggul Wulung Cilacap Berbasis Data Radiosonde Suharti Suharti; Abdul Haq; Noviarsyah Dasaprawira
Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer Vol. 6 No. 2 (2026): Juli: Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/juritek.v6i2.7629

Abstract

Weather prediction, particularly rainfall potential, plays a crucial role in supporting airport operations to minimize the risk of flight disruptions, particularly in coastal areas prone to extreme weather. This study aims to provide practical solutions for airport managers in anticipating operational disruptions due to rainfall by utilizing historical data and probabilistic models for weather condition classification. Rain potential prediction is performed using radiosonde index data representing atmospheric lability conditions, namely the Lifted Index (LI), K-Index (KI), Showalter Index (SI), and Total Totals Index (TT) as predictor variables. Data were obtained from the Tunggul Wulung Cilacap Meteorological Station database for the 2020–2024 period, then used in the model training and evaluation process by handling missing values and measuring performance using a confusion matrix. The results show that the Naïve Bayes machine learning method is capable of producing a rainfall potential prediction model with an accuracy of 71.56%. These findings are expected to support more timely and efficient decision-making and have the potential to be applied in an early warning system based on actual observations for disaster mitigation.
Perancangan Sistem Rekomendasi Konten Video Youtube Berdasarkan Minat Pengguna Menggunakan Metode Content-Based Filtering Venerdi, Neville; Ahmad Fitriansyah; Jamah Sari
Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer Vol. 6 No. 2 (2026): Juli: Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/juritek.v6i2.7635

Abstract

YouTube provides a large number of videos with diverse topics, but users still often face difficulties in finding content that matches their current interests. Based on a questionnaire involving 60 respondents, 83.3% of respondents stated that they often receive repetitive YouTube video recommendations, 86.7% stated that excessive search results make the search process less directed, and 88.3% were interested in using a recommendation system that presents videos based on specific interests. This study aims to design a YouTube video content recommendation system based on user interests using the Content-Based Filtering method. The proposed system uses YouTube video metadata, including title, description, hashtag, channel name, duration, view count, likes, publication date, thumbnail, and video URL. The dataset consists of 1,225 videos grouped into 9 categories and 49 subcategories. Sentence-BERT (SBERT) is applied to represent metadata and user-selected interests as semantic embedding vectors, while Cosine Similarity is used to calculate the similarity between user interest queries and video metadata. The system generates five top recommendations for each selected subcategory, combines the results, and ranks them based on the highest similarity score. The implementation includes category and subcategory selection, recommendation display, result filtering, and access to videos on YouTube. Black Box Testing shows that the main system functions run according to user needs. Therefore, the proposed system can help users explore YouTube videos more directly, specifically, and relevantly based on selected interests.
Implementasi Adaptive Neuro Fuzzy Inference System (AN-FIS) Dalam Peramalan Evaluasi Konsumsi Listrik Untuk Efisiensi Energi Di Gedung A FKIP UNTIRTA Dede Eful Ginanjar; Desmira Desmira; Irwanto Irwanto
Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer Vol. 6 No. 2 (2026): Juli: Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/juritek.v6i2.7636

Abstract

This research is motivated by the use of electrical energy that is not fully in accordance with the Energy Consumption Intensity (IKE) standard, where there are still rooms with excessive or suboptimal energy use. The study aims to evaluate and predict electrical energy consumption in Building A of the Faculty of Teacher Training and Education, Sultan Ageng Tirtayasa University in order to improve energy efficiency. The method used is quantitative research with a comparative approach, namely comparing manual calculations based on the IKE standard with the Adaptive Neuro Fuzzy Inference System (ANFIS) method. Data were obtained through observation and measurement of electrical power, room area, and duration of use which were then analyzed using Matlab with the stages of fuzzification, FIS formation, hybrid learning training, and evaluation using RMSE. The results showed that the ANFIS method produced a better level of accuracy than manual calculations. The lowest error value was obtained in the gbellmf membership function for training at 0.53 and gaussmf for testing at 0.45. These findings indicate that ANFIS is able to model nonlinear relationships effectively and has the potential to be applied as a support system for evaluating electrical energy efficiency