cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
tin.journal@fkpt.org
Editorial Address
Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
TIN: TERAPAN INFORMATIKA NUSANTARA
Published by Forum Kerjasama Pendidikan TInggi
ISSN : -     EISSN : 27227987     DOI : -
Core Subject : Economy, Health, Science, Education, Art, Social, Engineering,
Aerospace Engineering Arts Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Social Sciences Veterinary Other
Jurnal TIN: TERAPAN INFORMATIKA NUSANTARA memuat tentang Kajian Bunga Rampai dari berbagai ide dan hasil penelitian para peneliti, mahasiswa, dan dosen yang berkompeten di bidangnya dari berbagai disiplin ilmu seperti: Komputer, Informatika, Industri, Elektro, Telekomunikasi, Kesehatan, Agama, Pertanian, Pembelajaran, Pendidikan, Teknologi Pendidikan, Ekonomi dan Bisnis, Manajemen, Akuntansi, dan Hukum
Arjuna Subject : Umum - Umum
Articles 756 Documents
 68   69   70   71   72 
Implementasi MobileNet V2 untuk Klasifikasi Jenis Apel Berdasarkan Citra Digital Airlangga Marta Farizky; Achmad Noercholis
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10216

Abstract

Apple variety classification based on digital images is a challenging problem because some varieties have similar visual characteristics, such as color, shape, and surface texture of the fruit. This similarity can lead to misidentification when performed manually. This study aims to develop an apple variety classification model using the MobileNetV2 architecture with a transfer learning and fine-tuning approach. The dataset used consists of 1,237 apple images representing four varieties: Anna, Manalagi, Rome Beauty, and Granny Smith. After data cleaning to remove duplicate images, 1,050 images were obtained for use in the study. The pre-processing stage includes image resizing to 224 × 224 pixels, normalization, and texture enhancement using a combination of Unsharp Masking and the Sobel operator. To improve the model's generalization capability, data augmentation and class weighting were applied during the training process. The model was then evaluated using a confusion matrix, accuracy, precision, recall, and F1-score. The test results showed that the MobileNetV2 model achieved an accuracy of 99.37%, a precision of 99.48%, a recall of 99.07%, and an F1-score of 99.27%. Confusion matrix analysis showed that out of 158 test data, there was only one misclassification, namely the Rome Beauty image predicted as Anna. In addition, the model was successfully implemented into a web-based application using Streamlit so that it can be used to directly identify apple varieties. The results showed that MobileNetV2 is effective for classifying apple varieties with a high level of accuracy and good computational efficiency, so it has the potential to be applied to image-based fruit identification systems in agriculture.
Evaluasi Pseudo-Labeling IndoRoBERTa dan InSet Lexicon dengan SVM pada Komentar TikTok Yehezkiel Juandro Metta; Aswan Supriyadi Sunge; Asep Suprianto
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10243

Abstract

TikTok generates large volumes of public comments that can be used to identify trends in public opinion, including responses to the accident involving a vehicle used in the Free Nutritious Meal program. However, informal social media language and imbalanced class distributions may affect sentiment labeling and classification performance. This study evaluates sentiment pseudo-labels generated by IndoRoBERTa and InSet Lexicon through Support Vector Machine classification with the application of the Synthetic Minority Over-sampling Technique. A quantitative experimental approach was applied to 10,309 TikTok comments collected through Apify scraping. Since no human annotations were used as ground truth, the positive, negative, and neutral labels produced by both methods were treated as pseudo-labels. The research stages included filtering, preprocessing, pseudo-label generation, Term Frequency-Inverse Document Frequency feature extraction, an 80:20 data split, SMOTE application to the training data, SVM classification, and evaluation using accuracy, precision, recall, and F1-score. The results show that SVM reproduced the InSet Lexicon pseudo-labels most effectively, achieving an accuracy of 0.865 without SMOTE. After SMOTE was applied, precision increased to 0.870 while the F1-score remained at 0.865, and neutral-class recall increased from 0.767 to 0.807. These findings indicate that InSet Lexicon produced pseudo-labels that were more consistently learned by SVM on this dataset, while SMOTE primarily improved minority-class recognition.
Analisis Sentimen Penonton Terhadap Film Sore Istri dari Masa Depan pada Twitter Menggunakan Algoritma Support Vector Machine Alfaza Putra Adjie Ariefiansyah; Andri Firmansyah
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10244

Abstract

The development of social media has encouraged people to express their opinions about cinematic works openly, quickly, and in real time. Twitter, now known as X, has become one of the most widely used platforms for sharing brief film reviews, generating a large volume of opinion data that is difficult to analyze manually. This study aims to analyze audience sentiment toward the film Sore: Istri dari Masa Depan based on tweet data, apply the Support Vector Machine algorithm in the sentiment classification process, and evaluate the performance of the resulting model. The research data were collected through a tweet crawling process using keywords related to the film Sore: Istri dari Masa Depan from July 2025 to April 2026. A total of 7,467 tweets were analyzed through text preprocessing, sentiment labeling, feature weighting using Term Frequency-Inverse Document Frequency, and classification using Support Vector Machine. Model evaluation was conducted using a confusion matrix with accuracy, precision, recall, and F1-score metrics, using an 80:20 training and testing data split. The results showed that 6,822 tweets were classified as positive sentiment and 645 tweets as negative sentiment. The model achieved an accuracy of 90.75%, indicating that it was able to classify audience sentiment effectively. This study contributes by providing a computational approach to mapping public reception of Indonesian films through social media data, while also offering a basis for film industry practitioners to evaluate audience responses and develop data-driven promotional strategies.
Sistem Pendukung Keputusan Pemilihan Sepeda Motor Listrik Menggunakan Fuzzy AHP-TOPSIS dengan Pendekatan User-Driven Muhammad Habib; Yelfi Vitriani; Reski Mai Candra; Surya Agustian; Iwan Iskandar
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10260

Abstract

The growth of electric motorcycles in Indonesia, which is projected to reach more than 196,000 units by mid-2025, has created complexity in consumers’ purchasing decision-making processes due to the wide variety of technical specifications across brands. This study designs and develops a user-driven Android-based Decision Support System by integrating the Fuzzy Analytical Hierarchy Process (Fuzzy AHP) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to generate personalized recommendations for selecting electric motorcycles. The system evaluates 23 alternatives from seven brands with official dealers in Pekanbaru based on seven technical criteria: price, range, charging time, maximum speed, motor power, load capacity, and battery capacity. Criterion weights are determined dynamically through a 1–5 scale slider interface mapped to Triangular Fuzzy Numbers (TFN) and processed using Chang’s Extent Analysis Method (1996), while ranking is performed using TOPSIS. This study applies the Fuzzy AHP method to address the ambiguity in users’ subjective assessments, which are often not well accommodated by single crisp values in conventional AHP. The main contribution of this study lies in the simplification of the weight elicitation mechanism, which reduces 21 conventional pairwise comparisons to just seven direct slider inputs mapped into TFN form. Furthermore, this study successfully implemented this user-driven, slider-based mechanism into an Android-based decision support system (DSS) for selecting electric motorcycles that is directly accessible to end consumers. For system testing, all scenarios in the Black Box Testing (33 scenarios) were successfully executed without errors. Furthermore, an evaluation via User Acceptance Testing (UAT) using the USE Questionnaire framework on 10 respondents yielded an acceptability score of 83.2%, which falls into the “Highly Acceptable” category. Based on the Performance preference profile, the United RX6000 was determined to be the best alternative with a Closeness Coefficient value of 0.9377.
Rancang Bangun Alat Ukur Kualitas Air Sanitasi Berbasis ESP32-C6 dan Internet of Things Nur Kholis Nafis; Julman Notatema Waruwu; Aisyah Putri Harmelia; Asri Sarassufi Aisah; Daffa Maulana Kindi A.L; Purba M. Ahla Kurniawan; Muhammad Reynaldi Ilham; Bayu Widodo; Mamat Rahmat
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10261

Abstract

Sanitation water quality is one of the important factors affecting public health. Conventional water quality monitoring generally requires laboratory testing, which is relatively time-consuming, costly, and unable to provide real-time information. This study aims to design and develop an Internet of Things (IoT)-based sanitation water quality monitoring device using an ESP32-C6 microcontroller integrated with pH, total dissolved solids (TDS), turbidity, and temperature sensors. The research method consisted of system design, hardware implementation, sensor accuracy testing, and stability testing through repeated measurements. Accuracy testing was conducted by comparing sensor readings with reference measuring instruments, while stability testing was evaluated using standard deviation and precision (%RSD) values. The results showed that the pH sensor had an error rate of 0.24% and the temperature sensor had an error rate of 2.51%, where as the TDS sensor exhibited an error rate of 16.92%. Stability testing indicated that all sensors produced relatively small measurement variations, with precision values ranging from 0% to 2.53%. Testing on tap water, well water, and river water samples demonstrated that the system was able to distinguish water quality characteristics based on the measured parameters. The results indicate that the developed system is capable of performing real-time water quality monitoring and generating consistent measurement data during repeated observations. This study may serve as a basis for the further development of IoT-based sanitation water quality monitoring systems through improved sensor accuracy and the inclusion of additional water quality parameters in future research.
Pengujian Pengalaman Pengguna Platform LMS Menggunakan Metode UEQ pada Siswa SMP Alfin Maulid; Rio Setiawan; Ridian Gusdiana
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10269

Abstract

The implementation of Learning Management Systems (LMS) in rural Junior High Schools (SMP) faces environmental technical challenges and user oversights (human error). At SMP Negeri 2 Cikajang, the use of LMS for the Summative End-of-Semester Assessment (PSAS) is confronted with fluctuating internet connectivity and student login issues. The urgency of this study lies in the need for an evaluation using the User Experience Questionnaire (UEQ) method to diagnose the multidimensional impact of these technical issues, capturing both pragmatic quality and hedonic quality. This quantitative survey research aims to measure the user experience of the LMS using the UEQ method and to generate adaptive system workflow recommendations. From a population of 932 students, the sample was calculated using the Slovin formula and selected through Proportionate Stratified Random Sampling to ensure representativeness across grade levels (VII, VIII, IX), yielding 95 valid respondents. Data analysis using the UEQ Data Analysis Tool measured six main scales: Attractiveness, Perspicuity, Efficiency, Dependability, Stimulation, and Novelty. The analysis results show exceptionally high mean scores across all dimensions (> 0.8): Attractiveness (2.34), Perspicuity (2.29), Efficiency (2.13), Dependability (1.95), Stimulation (2.24), and Novelty (2.11). Based on the global benchmark analysis, all six dimensions are categorized as Excellent. This study contributes empirically to the evaluation of LMS user experience in rural junior high schools using the User Experience Questionnaire (UEQ), while providing adaptive system improvement recommendations that consider network limitations and the characteristics of early adolescent users. In conclusion, despite external infrastructure barriers, the LMS platform is perceived as highly positive, dependable, and motivating by students because users can distinguish external network constraints from the intrinsic quality of the application.
Analisis dan Optimasi Jumlah Dataset pada YOLOv8 untuk Inspeksi Stamping Otomatis Khairul Ma’mur; Tatyantoro Andrasto; Arief Arfriandi
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10302

Abstract

Quality inspection of stamping products in the manufacturing industry is generally performed manually, which may lead to errors caused by operator fatigue, inconsistent observations, and low inspection efficiency. This study aims to implement the You Only Look Once version 8 (YOLOv8) algorithm to automatically detect and classify stamping products into Good and Not Good (NG) categories. The research stages included dataset collection, data preprocessing, model training, validation, and real-time testing. To analyze the effect of dataset size on model performance, three training scenarios were conducted using 100, 1,134, and 1,552 images with identical training parameters. Model performance was evaluated using Precision, Recall, mean Average Precision at 50% Intersection over Union (mAP50), mean Average Precision at 50%–95% Intersection over Union (mAP50–95), and a confusion matrix. The results indicate that increasing the number of datasets improves the performance of the YOLOv8 model. The model trained using 1,552 images achieved the best performance, with a Precision of 99.8%, Recall of 100%, mAP50 of 99.5%, and mAP50–95 of 96.6%, representing an improvement of 11.7 percentage points in mAP50–95 compared with the model trained using 100 images, which achieved an mAP50–95 of 84.9%. These findings indicate that increasing the dataset size enhances the model's generalization capability in recognizing variations in stamping quality. The best-performing model was subsequently implemented in real-time testing using a laptop camera and was able to consistently detect and classify stamping products under various lighting conditions, achieving a testing accuracy of 90%.
Evaluasi User Experience Sistem Informasi SI-SELMA Menggunakan User Experience Questionnaire (UEQ) Haddad Alwi Situmorang; M. Khalil Gibran; Windy Halmania Hasibuan; Boi Dahlan Syahputra Padang; Amelia Sni Ramud
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10309

Abstract

The Student Electronic Correspondence Information System (SI-SELMA) is a digital administrative platform implemented by Universitas Islam Negeri Sumatera Utara to facilitate the management and issuance of various academic documents online. Although the system is operational and plays a crucial role in campus bureaucracy, no empirical evaluation has been conducted regarding the quality of its user interaction. This study aims to evaluate the user experience of SI-SELMA using the User Experience Questionnaire (UEQ) approach. Methodologically, this study employs a descriptive quantitative survey design, involving 147 active students from Universitas Islam Negeri Sumatera Utara (cohorts 2022 to 2025) selected through convenience sampling. The research instrument consists of 26 statement items evaluating six main scales: attractiveness, perspicuity, efficiency, dependability, stimulation, and novelty. Data analysis was performed using the UEQ Data Analysis Tool to process value transformations, aggregate scale means, and compare results against global benchmarks. Cronbach’s Alpha test results indicate that all variables possess good internal consistency, with scores exceeding 0.6. The findings confirm that SI-SELMA excels in functional aspects; four indicators successfully reached the Above Average level: perspicuity (1.23), dependability (1.29), efficiency (1.14), and stimulation (1.04). However, the visual design aspect shows clear weaknesses, where attractiveness (1.15) and novelty (0.65) fall specifically into the Below Average category. Thus, the platform is reliable in meeting students' administrative needs; however, improvements to the layout and user interface design are recommended to enhance visual appeal and user experience quality in future system development. This study also contributes empirical evidence on the application of the User Experience Questionnaire (UEQ) for evaluating electronic student correspondence systems in higher education and provides interface improvement recommendations based on the user experience evaluation results.
Implementasi dan Analisis Algoritma FIFO, FEFO, dan LIFO pada Sistem Automated Storage and Retrieval System (ASRS) Berbasis Internet of Things untuk Produk Minuman Kemasan Muhammad Daffa Fauzan; Tatyantoro Andrasto; Mario Norman Syah
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10316

Abstract

Warehouse management for packaged beverage products faces critical risks of expired products and human error in stock rotation. This research implements an IoT-based Automated Storage and Retrieval System (ASRS) integrating three stock rotation algorithms, FIFO, FEFO, and LIFO, in a single backend control platform using PHP, MySQL, ESP32 microcontroller, and QR Code scanner. Research and Development (R&D) method with Waterfall model was employed. Testing was conducted at the Electrical Engineering Laboratory of Semarang State University using 100 ml UHT milk products across 60 trials (20 per algorithm). Results show all three algorithms achieved 100% accuracy, and QR Code identification yielded 93.3% accuracy with an average response time of 287 ms. Edge case testing proved deterministic handling of identical expiry dates, simultaneous timestamps, empty stock, and full slots. FEFO proved most suitable for packaged beverage management by consistently prioritizing products with the nearest expiry date, minimizing spoilage risk. The main contributions of this research simultaneous integration of three stock rotation algorithms (FIFO, FEFO, LIFO) within a single IoT-based backend control platform, a deterministic SQL-based tiebreaker mechanism to eliminate ambiguity in identical-data conditions, and empirical validation of FEFO's superiority over FIFO and LIFO for packaged beverage products through comparative residual stock analysis.
Implementasi Smart Buoy untuk Prediksi Kualitas Air Tambak Udang dengan Double Exponential Smoothing Edi Edi; I Nyoman Tirtha Yuda; Maksy Sendiang; Deitje Sofie Pongoh
TIN: Terapan Informatika Nusantara Vol 7 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v7i1.10321

Abstract

White shrimp farming is highly dependent on water quality stability, particularly temperature and pH parameters that directly affect shrimp growth and survival. In practice, water quality monitoring in many shrimp ponds is still conducted manually and periodically, causing environmental changes to be detected too late for timely intervention. Furthermore, most existing monitoring systems only provide current condition information without predictive capabilities that can support preventive decision-making. This study aims to design and implement a Smart Buoy based on the Internet of Things for real-time water quality monitoring and short-term early warning generation. The proposed system integrates an ESP32 microcontroller, temperature and pH sensors, LoRa communication, Firebase cloud services, and a mobile application as the user interface. The Double Exponential Smoothing method was employed to predict temperature and pH conditions 30 minutes ahead, while model parameters were determined using a walk-forward validation approach. The results demonstrate that the system successfully performs continuous data acquisition, transmission, storage, and visualization of water quality information. Forecasting evaluation yielded Mean Absolute Percentage Error values of 0.62% for temperature and 0.32% for pH. The system also successfully delivered automatic danger and early warning notifications when water quality conditions were detected or predicted to exceed predefined safety thresholds. This study contributes to the development of an IoT-based shrimp pond water quality monitoring and prediction system by integrating a Smart Buoy for more representative data acquisition, the Double Exponential Smoothing method for short-term forecasting, and a mobile application that supports real-time monitoring and faster, more preventive decision-making in shrimp pond management.

Page 70 of 76 | Total Record : 756

 68   69   70   71   72 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol 6 No 12 (2026): May 2026 Vol 6 No 11 (2026): April 2026 Vol 6 No 10 (2026): March 2026 Vol 7 No 2 (2026): July 2026 Vol 7 No 1 (2026): June 2026 Vol 6 No 9 (2026): February 2026 Vol 6 No 8 (2026): January 2026 Vol 5 No 12 (2025): May 2025 Vol 5 No 11 (2025): April 2025 Vol 5 No 10 (2025): March 2025 Vol 6 No 7 (2025): December 2025 Vol 6 No 6 (2025): November 2025 Vol 6 No 5 (2025): October 2025 Vol 6 No 4 (2025): September 2025 Vol 6 No 3 (2025): August 2025 Vol 6 No 2 (2025): July 2025 Vol 6 No 1 (2025): June 2025 Vol 5 No 9 (2025): February 2025 Vol 5 No 8 (2025): January 2025 Vol 4 No 12 (2024): May 2024 Vol 4 No 11 (2024): April 2024 Vol 4 No 10 (2024): March 2024 Vol 5 No 7 (2024): December 2024 Vol 5 No 6 (2024): November 2024 Vol 5 No 5 (2024): October 2024 Vol 5 No 4 (2024): September 2024 Vol 5 No 3 (2024): August 2024 Vol 5 No 2 (2024): July 2024 Vol 5 No 1 (2024): June 2024 Vol 4 No 9 (2024): February 2024 Vol 4 No 8 (2024): January 2023 Vol 3 No 12 (2023): May 2023 Vol 3 No 11 (2023): April 2023 Vol 3 No 10 (2023): March 2023 Vol 4 No 7 (2023): December 2023 Vol 4 No 6 (2023): November 2023 Vol 4 No 5 (2023): October 2023 Vol 4 No 4 (2023): September 2023 Vol 4 No 3 (2023): August 2023 Vol 4 No 2 (2023): July 2023 Vol 4 No 1 (2023): June 2023 Vol 3 No 9 (2023): February 2023 Vol 3 No 8 (2023): January 2023 Vol 2 No 10 (2022): Maret 2022 Vol 3 No 7 (2022): December 2022 Vol 3 No 6 (2022): November 2022 Vol 3 No 5 (2022): October 2022 Vol 3 No 4 (2022): September 2022 Vol 3 No 3 (2022): August 2022 Vol 3 No 2 (2022): July 2022 Vol 3 No 1 (2022): June 2022 Vol 2 No 9 (2022): Februari 2022 Vol 2 No 8 (2022): Januari 2022 Vol 1 No 12 (2021): Mei 2021 Vol 1 No 11 (2021): April 2021 Vol 1 No 10 (2021): Maret 2021 Vol 2 No 7 (2021): Desember 2021 Vol 2 No 6 (2021): November 2021 Vol 2 No 5 (2021): Oktober 2021 Vol 2 No 4 (2021): September 2021 Vol 2 No 3 (2021): Agustus 2021 (in press) Vol 2 No 3 (2021): Agustus 2021 Vol 2 No 2 (2021): Juli 2021 Vol 2 No 1 (2021): Juni 2021 Vol 1 No 9 (2021): Februari 2021 Vol 1 No 8 (2020): Januari 2021 Vol 1 No 7 (2020): Desember 2020 Vol 1 No 6 (2020): November 2020 Vol 1 No 5 (2020): Oktober 2020 Vol 1 No 4 (2020): TIN: September 2020 Vol 1 No 3 (2020): TIN: Agustus 2020 Vol 1 No 2 (2020): TIN: Juli 2020 Vol 1 No 1 (2020): Juni 2020 More Issue