cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Dodi Siregar
Contact Email
dodi.729ar@gmail.com
Phone
+6281361223297
Journal Mail Official
jurnal.jitekh@gmail.com
Editorial Address
Unit Publikasi Jurnal (UPJ) Universitas Harapan Medan Jl. Imam Bonjol No. 35 Medan eMail: jurnal.jitekh@gmail.com
Location
Kota medan,
Sumatera utara
INDONESIA
JiTEKH (Jurnal Ilmiah Teknologi Harapan)
Published by Universitas Harapan Medan
ISSN : 23385677     EISSN : 25496646     DOI : 10.35447
Core Subject : Science, Engineering,
Civil Engineering, Building, Construction & Architecture Computer Science & IT Electrical & Electronics Engineering Engineering Mechanical Engineering
JITEKH merupakan jurnal ilmiah yang menyajikan artikel orisinal tentang pengetahuan dan informasi riset atau aplikasi riset dan pengembangan terkini dalam bidang keteknikan dan teknologi informasi. Ruang lingkup Jurnal JITEKH meliputi bidang Informatika, Teknik Mesin, Teknik Elektro, Sistem Informasi, Teknik Industri dan Teknik Sipil. Focus and Scope: Design Manufacture Konversi Energi Material Data analysis Natural Language Processing Artificial Intelligence Neural Networks Pattern Recognition Image Processing Genetic Algorithm Bioinformatics/Biomedical Applications Biometrical Application Content-Based Multimedia Retrievals Augmented Reality Virtual Reality Information System Game Mobile Data mining Artificial Intelligence Sistem Pendukung Keputusan IT Bussiness Incubation IT Governance Cloud Computing Dessision Support System Instrumentation and Control Electrical (Power) Electronics Engineering Industrial Engineering Optimasi Sistem Produksi Perencanaan Produksi dan Pengendalian Persediaan Penjadwalan dan Manajemen Operasi/Proyek Computer-Integrated Manufacturing System Sustainable Product Design and Manufacturing Penelitian Operasional dan Decision-Making Model Manajemen Teknologi Pengukuran Kerja, Faktor-Faktor Manusia dan Ergonomi Rekayasa dan Pengendalian Kualitas Sistem Logistik dan Supply Chain Management Perancangan dan Pengembangan Produk Concurrent Engineering Analisis Ekonomi Teknik Pemodelan Sistem dan Analisis Simulasi Perancangan Layout Fasilitas Knowledge Management Reliability and Maintenance Engineering Sistem dan Teknologi Informasi Rekayasa Pelayanan (Service Engineering) Technopreneurship dan Inovasi Aplikasi Model Stokastik dalam Teknik Industri Aplikasi Metode Metaheuristik dalam Teknik Industri Building Materials and Structures Constructions Technology Constructions Economy and Management Earthquake Engineering Environmental Engineering Renovation of Buildings Geotechnical Engineering Highway Engineering Hydraulic and Hydraulic Structures Road and Bridge Engineering Structural Engineering Surveying and Geo-Spatial Engineering Transportation Engineering Tunnel Engineering Urban Engineering and Economy Water Resources Engineering Urban Drainage
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 134 Documents
 10   11   12   13   14 
Analisis Sentimen E-Commerce Shopee Menggunakan Metode Support Vector Machine (SVM) untuk Mengevaluasi Kualitas Layanan Penjual Aidil Ramadani; Nur Azizah; Rahmat Shofan Razaqi
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1376

Abstract

The rapid growth of e-commerce generates a large volume of Shopee customer reviews, making manual evaluation inefficient and inconsistent. This study addresses the need for automated text classification to identify review polarity and support seller service evaluation. A labeled dataset of 800 Shopee reviews (600 positive, 200 negative) was collected from Kaggle. The texts were preprocessed using case folding, tokenization, stopword removal, and stemming to reduce noise and standardize writing. Reviews were converted into TF-IDF feature vectors (max_features=5,000; n-gram range 1-2) and classified using a Support Vector Machine (SVM) with an RBF kernel and class-weight balancing. The data were split with stratified sampling (80:20) to preserve label proportions in training and testing sets. Model performance was measured using accuracy, precision, recall, F1-score, and a confusion matrix. The classifier achieved 83.75% accuracy and produced stronger results for positive reviews, while negative reviews were more frequently misclassified due to class imbalance and diverse complaint expressions. As supporting documentation, a subset of reviews was prepared as screenshots and annotated in Roboflow, while the main sentiment evaluation remained based on TF-IDF feature extraction and SVM classification. Overall, TF-IDF combined with SVM provides a practical approach for monitoring customer sentiment and prioritizing seller service improvements over time.
Pengembangan Model Government Decision Intelligence (IC-Gov) Untuk Mendukung Pengambilan Kebijakan Pemerintah Berbasis Data Mohamad Jamil; Iis Hamsir Ayub Wahab; Seh Turuy
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1377

Abstract

Digital government transformation requires analytical capabilities that not only process data but also generate predictive information to support policy decision-making. This study develops IC-Gov as a Government Decision Intelligence approach that integrates Machine Learning, evidence retrieval, and AI-based synthesis to support the analysis of regional development priorities. The modeling process employs four development indicators: the number of 4G blank spots, the percentage of roads in good condition, the education index, and GRDP per capita, with development priorities classified into low, medium, and high categories. Three algorithms—Random Forest, XGBoost, and Gradient Boosting—were evaluated using accuracy, macro precision, macro recall, macro F1-score, confusion matrix, and ROC-AUC. The results show that Random Forest achieved an accuracy, macro precision, macro recall, and macro F1-score of 1.00, followed by Gradient Boosting with an accuracy of 0.95 and a macro F1-score of 0.95, and XGBoost with an accuracy of 0.87 and a macro F1-score of 0.85. The ROC-AUC values were 1.000, 1.000, and 0.992, respectively. Feature importance analysis indicates that GRDP per capita has the highest relative contribution across all three models. The prediction results are subsequently integrated into IC-Gov as predictive insights, combined with supporting evidence and AI-based synthesis to generate more contextual analytical information. The findings demonstrate that integrating predictive analytics and evidence within a Government Decision Intelligence framework has the potential to strengthen data-driven regional development policy decision support while maintaining human decision-makers as the final authority
Artificial Intelligence Berbasis Deep Learning untuk Prediksi Efisiensi Energi pada Sistem WFA Menggunakan Data Sintetis Dara Sawitri
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1468

Abstract

The implementation of the Work from Anywhere (WFA) system has shifted electricity consumption patterns from centralized office environments to distributed locations such as homes, personal devices, co-working spaces, and internet-based digital services. In Indonesia in 2026, this phenomenon has become increasingly visible due to the growth of online activities and household electronic device usage, which significantly affect national electricity demand. In practice, several institutions and universities have started facing challenges in measuring energy efficiency because electricity consumption is no longer concentrated in a single location. This study proposes an Artificial Intelligence-based deep learning approach to predict energy efficiency levels in WFA environments using multivariate synthetic data. The dataset was constructed from several variables, including daily working duration, number of active devices, room temperature, occupancy level, air conditioning usage, internet connection quality, electricity tariffs, and electricity emission intensity. Four models were evaluated, namely Random Forest as the baseline model, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a lightweight Transformer model. Simulation results indicate that the lightweight Transformer achieved the best performance with an MAE of 0.041, RMSE of 0.057, MAPE of 5.31%, and a coefficient of determination (R²) of 0.928. The evaluation values were obtained from simulation results of the models using synthetic WFA system data. Overall, the findings demonstrate that deep learning approaches have strong potential to support data-driven monitoring systems and decision-making processes for improving energy efficiency in modern digital working environments
Prioritas Perbaikan Kualitas UMKM Bawang Lanang Berbasis SPK dengan Integrasi Seven Tools dan AHP Nailul Izzah; Moh Ririn Rosyidi; Anik Rufaidah; Suparno Suparno
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1489

Abstract

Quality control in MSMEs within the agri-food sector still faces challenges in integrating root cause diagnosis with objective intervention prioritization. This study aims to integrate Seven Quality Control (7QC) Tools and the Analytical Hierarchy Process (AHP) in a sequential framework to prioritize quality improvement in Bawang Lanang MSMEs in Gresik, East Java. Data were collected through observation of ten production batches, interviews, and AHP questionnaires completed by four experts (owner, two senior workers, and an industrial extension worker). The 7QC Tools results revealed dominant defects: peeling (69.7%) and scorching (30.3%), with the process under statistical control (p-chart: CL=32%, UCL=41%, LCL=23%). The AHP analysis showed that the Human factor had the highest priority weight (0.438; CR=0.02), followed by Material (0.195), Machine (0.146), Method (0.132), and Environment (0.089). Critical sub-factors identified were a lack of formal worker training and the absence of written SOPs. Based on these priorities, an improvement plan was formulated using the 5W2H approach, targeting a 50% defect reduction within six months, equivalent to saving 148.5 kg of product per cycle and a potential profitability increase of 20–25%. The contribution of this study is an integrative 7QC-AHP model that enriches the MSME quality management literature and provides a measurable and participatory improvement roadmap.
Optimalisasi Proses Manajemen Produksi pada Pabrik Tempe Skala UMKM untuk Meningkatkan Efisiensi Operasional Baiq Juniarti Wahyuningsi; Hery Irwan
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1498

Abstract

Abstract-The Micro, Small, and Medium Enterprises (MSMEs) tempe industry plays a pretty important role in the local economy. But, many of these businesses face operational inefficiency problems because their production methods are still semi-traditional and not standardized. This study aims to analyze and optimize the production management process in MSMEs -scale tempe factories to improve their operational efficiency. Using a qualitative approach and case study method, data were collected through participatory observation, in-depth interviews with owners and workers, as well as operational documentation. Efficiency measurements were done comparatively, that is, before and after optimization, using parameters that include raw material productivity, target efficiency, process time (time study), and waste percentage. The research results show that reconstructing the workflow and standardizing task distribution successfully increased productivity significantly, from 4.9 pcs/kg to 8.9 pcs/kg of soybeans. Production efficiency also improved from 54.4% to 98.8%, along with a reduction in production cycle time from 10 hours to 8 hours. In addition, the level of waste due to defective products was reduced from 5.10% to 1.68%. This study proves that applying planned modern operational management principles can minimize waste and optimize production capacity in traditional food industries, without eliminating the flexibility that characterizes MSMEs.
Integrasi Teorema Bayes dan MOORA dalam Sistem Pendukung Keputusan Seleksi Penerima Beasiswa Sisilia Daeng Bakka Mau; Emerensiana Ngaga; Alfry Aristo Jansen Sinlae; Ign. Pricher A. N. Samane; Joseray A. Lopes Da Cruz; G. Melva Kurniaramadhan Adhia Lengary; Hendra Setiawan Oly Bunga
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1504

Abstract

The scholarship selection process involves multiple academic, social, and economic criteria, making decision-making increasingly complex. Manual selection procedures are prone to subjectivity, inconsistency, and limited transparency, potentially reducing the accuracy of scholarship allocation. This study aims to develop a hybrid Decision Support System (DSS) by integrating the Bayesian Theorem and the Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) method to improve the objectivity and efficiency of scholarship recipient selection. The Bayesian Theorem is employed in the initial stage to classify candidates into eligible and ineligible groups based on posterior probabilities, while MOORA is applied to rank eligible candidates through normalization, weighting, and optimization processes. The study used data from 20 scholarship applicants evaluated using eight criteria: academic achievement, non-academic achievement, community involvement, economic condition, parents' income, residence in underdeveloped, frontier, and outermost (3T) areas, disability status, and the number of family dependents. The classification results identified 14 candidates as eligible, while 6 candidates were excluded from the ranking stage, reducing the number of alternatives processed during optimization by 30%. Subsequently, the MOORA method generated the priority ranking of scholarship recipients based on the optimization value of each alternative. The findings demonstrate that the integration of the Bayesian Theorem and MOORA provides a more objective, transparent, and efficient scholarship selection process than conventional manual approaches. The proposed model can serve as an effective decision support tool for scholarship selection in higher education institutions.
LEARN MAP: Kerangka Kecerdasan Buatan untuk Klasifikasi Aktivitas Belajar Mahasiswa dan Pemetaan Potensi Akademik Ita Margaretta Br Tarigan; Siti Jamilah Br Tarigan; Raheliya Br Ginting
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1507

Abstract

The digital transformation of higher education has generated large volumes of student activity data, most of which are stored as unstructured text. These data have significant potential to provide insights into learning patterns, competencies, and academic potential; however, conventional approaches often fail to capture contextual meaning and semantic relationships within student activity records. This study proposes LEARN MAP (Learning Activity and Academic Potential Mapping), an artificial intelligence framework based on Natural Language Processing (NLP) and Bidirectional Encoder Representations from Transformers (BERT) to automatically classify student learning activities and map academic potential. The study utilized a dataset of 8,954 student activity records collected from learning and Independent Learning–Independent Campus (MBKM) programs. The research process consisted of data collection, text preprocessing, BERT fine-tuning, activity classification, soft-skill mapping, and academic potential analysis. The results demonstrate that the BERT model achieved an accuracy of 92.31%, precision of 91.27%, recall of 90.84%, and F1-score of 91.05% in classifying student activities. The findings indicate that student activities were predominantly associated with communication, community engagement, collaboration, and research. Furthermore, the soft-skill mapping revealed that communication and self-directed learning were the most developed competencies, while most students were categorized as having moderate to high academic potential. The novelty of this study lies in the integration of BERT-based activity classification with soft-skill and academic potential mapping within a unified analytical framework. LEARN MAP has the potential to support data-driven academic decision-making and advance digital transformation initiatives in higher education.
Vision-based On Board Obstacle Detection System (VOODS) pada Sarana Perkeretaapian Menggunakan Pantauan Kamera Diva Trisna; Sutrisno; Joko Hariyono
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1510

Abstract

Urban railway industries face various safety challenges, including potential collisions, vehicles crossing rail tracks, and foreign objects on the track. Conventional inspection systems relying on train operators have limitations under restricted visibility and high speeds. This study develops a camera-based Vision-based On Board Obstacle Detection System (VOODS) using the YOLOv8 segmentation algorithm capable of detecting and classifying obstacles in real-time on railway tracks. The system utilizes existing CCTV cameras on trains, Ethernet network as communication channel, and a mini PC as the processing unit. A dataset was collected from the KRL Jabodetabek operational environment under morning and daytime lighting conditions, comprising 300 images (240 training and 60 validation) across four classes (Rail, Train, Human, Car). Annotation was performed using the LabelMe (Anaconda) platform, considering data confidentiality since the entire dataset is stored on the researcher’s local PC. The yolov8m-seg model was trained via Google Colaboratory with epochs=150, imgsz=1024, and patience=30. Danger zone determination is performed dynamically using the rail segmentation mask as Region of Interest (ROI); a warning subsystem then checks overlap between rail mask and object mask using bitwise AND operation to determine on-track presence. This approach refers to the clearance profile defined in Indonesian Ministerial Regulation PM No. 60 Year 2012. Evaluation results show a Box mAP@0.5 of 0.959 across all classes. Per-class performance: Rail 0.995, Train 0.989, Human 0.933, and Car 0.918. Confusion Matrix analysis shows a True Positive Rate of 1.00 for Rail, 0.96 for Train and Car, and 0.88 for Human. The warning subsystem was successfully tested on operational video and can trigger alerts when a human enters the rail area. The high Recall value is positive because, in railway safety context, Recall is more critical than Precision. The developed VOODS contributes significantly to improving operational safety of urban railway transportation in Indonesia
IoT-Based Early Detection System for Under Voltage and Over Voltage Protection on Railway Passenger Information Display Systems Budi Artono; Yuli Prasetyo; Agung Catur Prasetyo
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1511

Abstract

The reliability of the Passenger Information Display System (PIDS) is essential for ensuring safety, passenger comfort, and service quality in railway transportation. In Passenger Coach 612, the running text display delivers real-time travel information, operational status, and safety messages. However, unstable power supply conditions, particularly under-voltage and over-voltage, frequently cause display malfunctions, operational interruptions, and hardware damage. This study proposes an Internet of Things (IoT)-based protection and monitoring system to detect voltage abnormalities and prevent equipment failure. The system employs an ESP32 microcontroller as the main controller, an INA219 sensor for voltage and current measurement, and a relay module for automatic protection. Protection thresholds were set at 4.3 V for under-voltage and 5.7 V for over-voltage based on the EN 50155 standard and field observations. Operational data are transmitted in real time to an IoT platform and a Realtime Database, enabling remote web-based monitoring. Experimental results show that the proposed system accurately detects voltage disturbances, automatically disconnects the power supply under abnormal conditions, and provides reliable real-time monitoring. Sensor calibration yielded a correction factor of K = 0.981, with a voltage measurement error of only 0.02 V compared with a reference digital multimeter. The proposed system improves the reliability of the running text display, enhances maintenance efficiency through continuous remote monitoring, and contributes to safer and more reliable railway passenger information services.
Evaluasi Terintegrasi Rembesan dan Stabilitas Bendungan Raknamo: Pembandingan SEEP/W–V-Notch dan Respons terhadap Skenario Pembebanan Rizal Akri Boik; Indradhi Lasmana; Amandus Jong Tallo
JiTEKH Vol. 14 No. 2 (2026): September 2026
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/jitekh.v14i2.1570

Abstract

Dam-safety assessment requires integrated interpretation of numerical outputs and field monitoring while recognizing whether the compared observations represent equivalent flow domains. This study evaluates seepage at Raknamo Dam for two reservoir states, 99.68 and 104.18 m above sea level, together with slope stability under static, Operating Basis Earthquake (OBE), Maximum Design Earthquake (MDE), and rapid-drawdown conditions. SEEP/W yielded unit-width discharges of 3.0587×10⁻⁶ and 4.2983×10⁻⁶ m³/s/m. Scaling by the dam length produced section-equivalent values of 0.001376 and 0.001933 m³/s, whereas V-notch monitoring recorded 0.00360 and 0.00992 m³/s. Because longitudinal uniformity and equivalence between the modeled section and the V-notch catchment cannot be demonstrated, these quantities are not treated as equivalent observations for model validation or error estimation. V-notch data are therefore reported as independent operational monitoring evidence alongside the numerical outputs. SLOPE/W safety factors ranged from 2.082–2.504 under static conditions, 1.888–2.068 under OBE, and 1.257–1.400 under MDE. The two upstream MDE results, 1.259 at 99.68 m and 1.257 at 104.18 m, are considered practically indistinguishable at the available reporting precision because no sensitivity or uncertainty analysis was performed. The final rapid-drawdown condition after 18 h yielded a safety factor of 2.417, while the minimum factor of safety during the transient history is unavailable. The study demonstrates the value of complementary, but explicitly non-equivalent, monitoring and modeling evidence and clarifies the inference limits imposed by incomplete monitoring metadata and archived numerical-model information.

Page 13 of 14 | Total Record : 134

 10   11   12   13   14 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol. 14 No. 2 (2026): September 2026 Vol. 14 No. 1 (2026): March 2026 Vol. 13 No. 2 (2025): September 2025 Vol. 13 No. 1 (2025): March 2025 Vol. 12 No. 2 (2024): September 2024 Vol. 12 No. 1 (2024): March 2024 Vol 11 No 2 (2023): September 2023 Vol 11 No 1 (2023): Maret 2023 Vol 10 No 2 (2022): September 2022 Vol. 10 No. 1 (2022): Maret 2022 Vol 9 No 2 (2021): September 2021 Vol 9 No 1 (2021): Maret 2021 Vol. 8 No. 2 (2020): September 2020 Vol. 8 No. 1 (2020): Maret 2020 Vol 7 No 2 (2019): September 2019 Vol. 7 No. 1 (2019): Maret 2019 More Issue