cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Teguh Susyanto
Contact Email
teguh@sinus.ac.id
Phone
+62271-716500
Journal Mail Official
tikomsin@sinus.ac.id
Editorial Address
KH Samanhudi 84-86, Laweyan, Surakarta, 57142
Location
Kota surakarta,
Jawa tengah
INDONESIA
Jurnal TIKOMSIN (Teknologi Informasi dan Komunikasi Sinar Nusantara)
Published by STMIK Sinar Nusantara Surakarta
ISSN : -     EISSN : 26207532     DOI : http://dx.doi.org/10.30646/tikomsin
Core Subject : Science,
Computer Science & IT
Jurnal Tikomsin merupakan terbitan berkala hasil penelitian dalam bidang ilmu komputer mencakup disiplin ilmu teknologi informasi meliputi Sistem Pendukung Keputusan, Kecerdasan buatan, Data mining, Jaringan Komputer etc. Majalah ini diterbitkan secara periodik dua kali dalam setahun yaitu bulan April dan Oktober dan masing-masing terbitan sebanyak 9 artikel per issue.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 251 Documents
 22   23   24   25   26 
ANALISIS KOMPARATIF ALGORITMA SUPERVISED LEARNING UNTUK KLASIFIKASI SENTIMEN MULTICLASS TREN KENDARAAN LISTRIK Lestari, Verra Budhi; Rizki, Sestri Novia; Nasution, Vani Maharani
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1100

Abstract

This research is motivated by the high complexity of public opinion regarding electric vehicle (EV) trends, which can no longer be adequately represented through binary classification; however, a gap remains in the literature regarding the most efficient multiclass classification models within this domain. The study aims to conduct a comparative analysis of Support Vector Machine (SVM), Logistic Regression (LR), Multinomial Naive Bayes (MNB), and K-Nearest Neighbor (KNN) to determine the best model based on accuracy, precision, recall, and computational efficiency. Data consisting of 1,517 textual public opinions from social media were processed through stages including data cleaning, tokenization, stopword removal, and TF-IDF feature extraction. The results indicate that SVM achieved the best performance with an accuracy of 0.781 and an F1-score of 0.595, reflecting model stability and a good balance between precision and recall. Logistic Regression demonstrated superior precision (0.843) but lower recall, while MNB showed good computational efficiency despite moderate performance. Conversely, KNN yielded the lowest performance due to limitations in handling high-dimensional and sparse data. Further analysis reveals that all models struggled with the neutral class, indicating data imbalance and class similarity. This study contributes to the limited literature on multiclass sentiment evaluation in the EV domain and provides strategic insights into the trade-offs between model complexity, efficiency, and performance. These findings serve as a foundation for developing effective sentiment analysis systems to support decision-making related to electric vehicle trends.
PEMANFAATAN PLATFORM METAVERSE UNTUK VISUALISASI PERENCANAAN PARIWISATA PESISIR TERINTEGRASI Atmojo, Wahyu Tisno; Olivia, Deasy; Ayunda, Afifah Trista
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1082

Abstract

Using immersive technology in regional planning is now essential to provide an accurate picture of how areas will develop in the future. This study aims to design and develop a Virtual Reality (VR) Tour application that visualizes the integrated coastal tourism plan in Tangerang Regency. The coastal area of Tangerang has a lot of potential but needs more interactive social media communication to involve stakeholders and the community in planning. The development method used is the Multimedia Development Life Cycle (MDLC), which consists of six stages: concept, design, collecting materials, assembly, testing, and distribution. The development was done using Roblox Studio because of its strengths in rendering multi-user environments and the ease of access across different devices. The result of this research is a VR application that allows users to explore a digital prototype of the tourism area, including infrastructure facilities and mangrove conservation areas, in an immersive way. Testing the app showed that using VR devices gives a more detailed spatial experience compared to traditional models or 2D maps. This study concludes that using Roblox Studio with the MDLC method is effective in speeding up the process of creating VR prototypes for coastal tourism planning that is both communicative and educational.
A COMPUTER VISION APPROACH FOR CLASSIFYING CALIFORNIA PAPAYA RIPENESS USING K-NEAREST NEIGHBOR Wulandari, Tyas; Prabowo, Iwan Ady; Utami, Yustina Retno Wahyu; Raharja, Bayu Dwi; Wijayanto, Hendro
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1091

Abstract

Determining the ripeness level of California papaya is important for harvest decisions, sorting, distribution, and spoilage control. In practice, ripeness identification is still commonly performed visually and is therefore subjective. This study aims to develop a digital image-based classification system for California papaya ripeness using the K-Nearest Neighbor (K-NN) algorithm with Hue and Saturation features in the Hue Saturation Value (HSV) color space. The dataset consists of 90 primary images, divided into 60 training images and 30 testing images, with four ripeness classes: unripe, half-ripe, ripe, and rotten. All images were captured using a Xiaomi Mi A2 Lite smartphone and cropped to 1436 × 1000 pixels. Classification was conducted using Euclidean distance. The value of k was selected empirically through trial and error in the original study, and k = 9 was retained because it produced the most stable result on the available data while reducing the potential for class ties. The evaluation produced 22 correct predictions out of 30 test images, resulting in an accuracy of 73.33%. This revised manuscript strengthens the methodological reporting by clarifying parameter selection, documenting the data distribution and providing a literature-based comparison with alternative methods, such as Support Vector Machine (SVM) and Convolutional Neural Network (CNN). The findings suggest that K-NN with HSV features remains a feasible, low-cost baseline, although its performance should be improved through larger datasets, per-class evaluation reporting, and head-to-head comparisons on the same dataset.
FRAMEWORK LEARNING MANAGEMENT SYSTEM BERBASIS MICROLEARNING UNTUK MENINGKATKAN EFEKTIVITAS PEMBELAJARAN PADA PENDIDIKAN NON-FORMAL (STUDI KASUS PADA LKP) Saputro, Indrawan Ady; Aziz, Riyan Abdul; Widiyanti, Sri; Purwidiantoro, Moch Hari
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1101

Abstract

The rapid development of digital learning technologies requires innovative systems that can improve learning effectiveness, particularly in non-formal education institutions such as Training and Course Centers (LKP). However, existing learning systems often lack structured mechanisms to ensure gradual, measurable mastery of competencies. Therefore, a microlearning-based Learning Management System (LMS) integrated with a sequential mastery approach is proposed. This study aims to design and implement a microlearning-based LMS to enhance learning effectiveness in non-formal education settings. The system supports step-by-step delivery of learning to ensure progressive achievement of competency. The research methodology includes requirements analysis, system design using the Unified Modeling Language (UML), web-based implementation, and system evaluation using Black-Box Testing, the System Usability Scale (SUS), and pre- and post-test assessments. The results show that all system functions operate as intended. The usability evaluation obtained a SUS score of 78.33, categorized as Good and Acceptable. Learning effectiveness increased significantly, with an average score improvement of 25.67 points (45.03%) and an N-Gain value of 0.60 (moderate category), while achieving a 100% completion rate. In conclusion, the developed LMS is feasible and effective in improving learners’ competencies in non-formal education environments and offers a practical solution for digital learning transformation in LKP.
MODEL PERAMALAN PENJUALAN MENGGUNAKAN PENDEKATAN WEIGHTED MOVING AVERAGE PADA UMKM KOPI Lylla, Cantika Putri; Vulandari, Retno Tri; Kusumaningrum, Andriani
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1077

Abstract

Sales forecasting plays a critical role in supporting effective inventory management, particularly for small and medium enterprises (SMEs) in the coffee sector, where demand exhibits fluctuating patterns over time. Inaccurate demand estimation may lead to stock shortages, resulting in lost sales opportunities, or overstocking, which increases holding costs and product waste. Therefore, a reliable and accurate forecasting model is required to support optimal inventory planning and operational efficiency. This study aims to develop and implement a sales forecasting model using the Weighted Moving Average (WMA) method and to evaluate its predictive accuracy. The WMA method, as a time series approach, assigns different weights to historical data, emphasizing more recent observations to better capture short-term trends. Historical coffee sales data were utilized as the basis for model development. Forecast accuracy was evaluated using the Mean Absolute Percentage Error (MAPE). The results indicate that the WMA model provides a high level of accuracy, with a forecast value of approximately 22,914 units for the subsequent period and a MAPE value of 0.29% using weight parameters of 0.7, 0.2, and 0.1. This level of accuracy is categorized as very high, demonstrating that the proposed model is effective and reliable for supporting inventory decision-making and improving operational performance in SMEs.
ANALYSIS OF SPATIAL DISTRIBUTION AND SERVICEABILITY OF OFFICIAL POLLING STATIONS USING GIS AND WEBGIS IN NABIRE DISTRICT Prayitno, Gunawan; Majid, Eka Melani
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1099

Abstract

Temporary waste collection sites play an important role in supporting urban waste management services. However, the spatial distribution and service coverage of official temporary waste collection sites in Nabire District have not been comprehensively evaluated. This study aims to analyze the spatial distribution and service coverage of official temporary waste collection sites using Geographic Information System (GIS) and to implement the results in an interactive WebGIS. A quantitative spatial approach was applied using official TPS point data, landfill location data, administrative boundary data, and GIS-based spatial processing. The analysis included location mapping, Nearest Neighbor Analysis (NNA), 500-meter buffer analysis, dissolve processing, and administrative overlay. The results showed that the distribution pattern of official temporary waste collection sites tends to be clustered, with an NNA value of 0.7636 and a Z-score of -2.02. The 500-meter service coverage reached only 13.14 km² of the 205.26 km² study area, equal to 6.40%, while 93.60% remained outside the service range. The novelty of this study lies in integrating spatial distribution analysis, service coverage evaluation, and WebGIS visualization to support district-scale waste facility planning.
FLASH CARD AUGMENTED REALITY BERBASIS MARKER UNTUK MENINGKATKAN EKSPLORASI ILMIAH DAN PEMAHAMAN KOGNITIF PADA ANAK USIA DINI Caesar, Meisya; Putri, Astrid Novita; Harsadi, Paulus
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1090

Abstract

Eksplorasi ilmiah dalam perkembangan kognitif adalah proses pada anak-anak, khususnya pada usia dini untuk belajar dan memahami dunia di sekitar mereka dengan observasi, eksperimen, dan penalaran ilmiah. Eksplorasi ini melibatkan aktivitas yang mendorong siswa untuk bertanya, bereksperimen, dan menemukan jawaban secara mandiri maupun bersama teman teman. Hal ini diharapkan dapat membantu perkembangan kemampuan berpikir dan pembelajaran mereka. Diharapkah para siswa dapat mengetahui keefektifan media pembelajaran anak usia dini berbasis Teknologi Augmented Reality untuk mengimplementasikan marker-based pada flashcard sebagai alat pembelajaran. Flashcard pada augmented reality ini dirancang untuk memberikan informasi mengenai jenis buah, warna buah dan jumlah buah melalui interaksi visual yang menarik dan interaktif. Sehingga memudahkan dalam pembelajaran pada anak usia dini, augmented reality menawarkan potensi inovatif untuk meningkatkan kualitas pembelajaran. Anak-anak di TK Mekarsari mengalami beberapa permasalahan salah satunya adalah perkembangan kognitif yaitu susah dalam memahami warna-warna pada suatu benda atau objek. Sehingga memerlukan Augmented Reality ini untuk membantu anak pada pembelajaran dengan menggunakan Unity 3D dan Vuforia. Hasil penelitian ini diharapkan memberikan kontribusi dalam mengeksplorasi ilmiah dalam perkembangan kognitif melalui pendekatan teknologi yang inovatif dan efektif, serta meningkatkan kualitas belajar pada anak. Aplikasi ini juga dapat menjadi model untuk pengembangan alat pembelajaran serupa di berbagai institusi pendidikan anak usia dini.
IDENTIFIKASI POLA KECELAKAAN LALU LINTAS DENGAN K-MEANS CLUSTERING Bandhaso, Victor; Wati, Masna; uddin, Havil
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1037

Abstract

Traffic accidents represent a complex issue with significant social and economic impacts. This study aims to identify temporal patterns of traffic accidents based on temporal and demographic attributes using the K-Means Clustering algorithm applied to 9,659 accident records in Central Java Province in 2024. Time attributes were converted to decimal format, while occupational data for the involved parties were transformed into numerical codes to enable clustering analysis. The K-Means Clustering algorithm was then employed to generate cluster models. Cluster 0 is characterized by an afternoon peak in incident time around 18.10, with the closest encoded occupational category corresponding to TNI–POLRI personnel. Cluster 1 consists of an average incident occurring at 06.26, predominantly involving homemakers. Cluster 2 is dominated by homemakers, with incidents generally occurring around 17.03. Cluster 3 shows the dominance of TNI–POLRI personnel, with incidents most frequently occurring at 07.19. These findings indicate that the most frequently involved occupational groups are military/police personnel and homemakers, both of which exhibit high mobility during peak hours and also threaten officers who are supposed to maintain traffic order.
PENERAPAN METODE SIMPLE ADDITIVE WEGHTHING (SAW) DALAM EVALUASI KUALITAS RENDANG BERDASARKAN KRITERIA PRODUK DAN KEPUASAN KONSUMEN Silvilestari, Silvilestari; Widya Perdana, Rika
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1089

Abstract

The increasing variety of rendang products available in the market has created challenges for consumers in identifying products with the best quality. Product evaluation cannot be based on a single aspect, as rendang quality is influenced by multiple criteria, including taste, aroma, color, spice composition, shelf life, price, and consumer satisfaction. The involvement of numerous assessment criteria often leads to subjective and inconsistent judgments. This study aims to develop a Decision Support System (DSS) for evaluating rendang quality and identifying the most suitable product based on measurable criteria. The method applied in this research is Simple Additive Weighting (SAW), selected for its capability to process multi-criteria decision-making through weighted evaluation. Data were collected from observations and respondent assessments of several rendang alternatives, followed by normalization and weighted calculations to determine preference values. The findings demonstrate that the SAW method can generate an objective and systematic ranking of rendang products. The highest preference score was obtained by alternative XIII with a value of 0.97, while the lowest score was recorded by alternative IV with 0.56. These results indicate that the proposed method is effective in distinguishing product quality based on the established evaluation criteria. 
ANALISIS KOMPARATIF DECISION TREE, K-NEAREST NEIGHBOR, SUPPORT VECTOR MACHINE, DAN RANDOM FOREST UNTUK PREDIKSI OBJEK BERBASIS FITUR NUMERIK Rachmatsyah, Agus Dendi; Al Kodri, Ari Amir; Wijaya, Benny
Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN) Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026
Publisher : STMIK Sinar Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30646/tikomsin.v14i1.1098

Abstract

This study addresses the problem of object classification using numerical feature representations in machine learning environments. The research aims to compare the performance of four supervised learning algorithms, namely Decision Tree, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forest, in predicting object classes. The methodology consists of data preprocessing, normalization using Min-Max Scaling, model training, and evaluation using accuracy, precision, recall, and F1-score. A dataset of 2,400 samples with 18 numerical features and four object classes was used, with an 80:20 train-test split and cross-validation for robustness. The results show that Random Forest achieved the highest performance with 95.1% accuracy and 0.949 F1-score, followed by SVM with 93.2% accuracy. KNN and Decision Tree achieved 90.4% and 88.1% accuracy, respectively.The novelty of this study lies in the structured experimental pipeline and comprehensive multi-metric evaluation combined with computational efficiency analysis for object prediction using tabular data.It can be concluded that ensemble-based methods such as Random Forest provide superior generalization and stability for heterogeneous object data.

Page 25 of 26 | Total Record : 251

 22   23   24   25   26 

Filter by Year

2013 2026


Reset
Filter By Issues
All Issue Vol 14, No 1 (2026): Jurnal Tikomsin, Vol 14, No.1, April 2026 Vol 13, No 2 (2025): Jurnal Tikomsin, Vol 13, No.2, Oktober 2025 Vol 13, No 1 (2025): Jurnal Tikomsin Vol 12, No 2 (2024): Jurnal TIKomSiN Vol 12, No. 2 Oktober 2024 Vol 12, No 1 (2024): Jurnal TIKomSiN Vol 12, No. 1 April 2024 Vol 11, No 2 (2023): Jurnal Tikomsin, Vol. 11, No. 2, Oktober 2023 Vol 11, No 1 (2023): Jurnal TIKomSiN, Vol. 11, No. 1, April 2023 Vol 10, No 2 (2022): Jurnal TIKomSiN, Vol. 10, N0. 2, Oktober 2022 Vol 10, No 1 (2022): Jurnal TiKomSiN, Vol. 10, No. 1, April 2022 Vol 9, No 2 (2021): Jurnal TiKomSiN, Vol. 9, No. 2, 2021 Vol 9, No 1 (2021): Jurnal TIKomSiN, Vol.9, No. 1, 2021 Vol 8, No 2 (2020): Jurnal TIKomSiN, Vol.8, No. 2, 2020 Vol 8, No 1 (2020): Jurnal TiKomSiN, Vol.8, No. 1, 2020 Vol 7, No 2 (2019): Jurnal TiKomSiN, Vol.7, No. 2, 2019 Vol 7, No 1 (2019): Jurnal TiKomSiN Vol 6, No 2 (2018): Jurnal TIKomSiN Vol 6, No 1 (2018): Jurnal TiKomSiN Vol 5, No 2 (2017): Jurnal TiKomSiN Vol 5, No 1 (2017): Jurnal TiKomSiN Vol 4, No 2 (2016): JURNAL TIKomSiN Vol 4, No 1 (2016): JURNAL TIKomSiN Vol 3, No 2 (2015): JURNAL TIKomSiN Vol 3, No 1 (2015): JURNAL TIKomSiN Vol 2, No 2 (2014): Jurnal TIKomSiN Vol 2, No 1 (2014): JURNAL TiKomSiN Vol 1, No 2 (2013): Jurnal TIKomSiN Vol 1, No 1 (2013): Jurnal TIKomSiN More Issue