cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
semdejafet1908@gmail.com
Editorial Address
-
Location
Kota adm. jakarta timur,
Dki jakarta
INDONESIA
JITK (Jurnal Ilmu Pengetahuan dan Komputer)
Published by STMIK Nusa Mandiri
ISSN : -     EISSN : 25274864     DOI : -
Core Subject : Science,
Computer Science & IT
Kegiatan menonton film merupakan salah satu cara sederhana untuk menghibur diri dari rasa gundah gulana ataupun melepas rasa lelah setelah melakukan aktivitas sehari-hari. Akan tetapi, karena berbagai alasan terkadang seseorang tidak ada waktu untuk menonton film di bioskop. Dengan bantuan media internet, berbagai macam aplikasi nonton film android sangat mudah dicari. Hanya bermodalkan smartphone saja para penonton film dapat streaming berbagai macam jenis film di mana saja dan kapan saja mereka inginkan. Akan tetapi, karena banyaknya pilihan aplikasi nonton film android yang bisa digunakan, terkadang seseorang bingung memilihnya. Untuk itu, diperlukan suatu sistem pendukung keputusan yang dapat digunakan para pengguna sebagai alat bantu pengambilan keputusan untuk memilih dengan berbagai macam kriteria yang ada. Salah satu metode yang digunakan adalah metode Analytical Hierarchy Process (AHP). AHP melakukan perankingan dengan melalui penjumlahan antara vector bobot dengan matrik keputusan dengan tujuan agar hasil yang diberikan lebih baik dalam menentukan alternatif yang akan dipilih. Berdasarkan hasil penelitian yang dilakukan oleh 36 sampel responden didapatkan kriteria konten menjadi prioritas pertama pengguna untuk memilih aplikasi nonton film android dengan nilai bobot sebesar 0,224. Sedangkan Netflix menjadi alternatif dengan prioritas pertama keputusan pengguna dalam memilih aplikasi nonton film android dengan nilai bobot sebesar 0,352.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 543 Documents
 50   51   52   53   54 
WASTE CLASSIFICATION USING TRANSFER LEARNING WITH MOBILENETV2 TO SUPPORT ENVIRONMENTAL MANAGEMENT Muhammad Trihardyansyah; M Safii; Sundari Retno Andani
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.7757

Abstract

Efficient waste management requires an accurate automatic classification system for organic and recyclable categories. This study aims to develop a deep learning-based waste classification model using the MobileNetV2 architecture with a transfer learning approach. The main contribution of this study lies in the modification of the architecture through fine-tuning techniques and the integration of a 0.5 dropout layer specifically designed to address the problems of overfitting and class imbalance in waste image data. Test results show that the optimized MobileNetV2 model significantly improves classification performance, achieving an accuracy of 93%. This proposed model is proven to be more adaptive and substantially superior compared to standard architectures and comparable architectures such as ResNet.
BITCOIN PRICE PREDICTION WITH TECHNICAL INDICATORS: A HYBRID TRANSFORMER-RIDGE REGRESSION APPROACH Dio Richard Prastiyo; Muhammad Zaky Darajat; Christian Sri Kusuma Aditya
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.7789

Abstract

Bitcoin has emerged as the dominant cryptocurrency, exhibiting rapid adoption alongside extreme price volatility that complicates investment strategies, risk management, and regulatory decision-making. While prior hybrid studies have predominantly combined multiple deep learning components such as CNN–LSTM or Transformer–GRU architectures, the integration of a deep neural architecture with a regularized linear model remains underexplored in Bitcoin price forecasting. To address this gap, this study proposes a hybrid framework combining a Transformer neural network with Ridge Regression, wherein the Transformer captures nonlinear temporal dependencies while Ridge Regression introduces L2 regularization to mitigate overfitting and enhance interpretability—an integration explicitly motivated by the bias–variance trade-off. The model is trained on technical indicators including MACD, Bollinger Bands, and RSI, and an ensemble weighting parameter α is systematically optimized via grid search. Empirical evaluation demonstrates that the hybrid model consistently outperforms standalone baselines, achieving an MAE of 1,251.572, RMSE of 1,623.004, R² of 0.991, and MAPE of 1.701%, with performance differences confirmed statistically via the Diebold–Mariano test. Economic validation reveals that the hybrid model is the only strategy to demonstrate statistically significant directional accuracy, although absolute trading returns remain below passive benchmarks under trending market conditions—a dissociation consistent with established findings in financial forecasting research. These results indicate that the model's primary contribution lies in forecast reliability and directional signal quality rather than return maximization under simple trading rules. Sensitivity to macroeconomic shocks and computational demands remain limitations for real-time deployment, suggesting directions for future research.
WEB APP FOR BANSOS DISTRIBUTION USING FINGERPRINTS AND PHOTO TIMESTAMPS FOR VERIFICATION AND MONITORING Miri Ardiansyah; Aria Armada D.J; Farhan Hamdallah; Khoiriyah
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.7945

Abstract

The implementation of fingerprint biometric sensors as a substitute for identity cards in the process of distributing social assistance is important because the requirement to bring an original or photocopy of an electronic identity card (E-KTP) is inconvenient for recipients. In addition to being inefficient, this method is also not in line with the government’s digitalisation initiatives. Furthermore, the distribution of social assistance is often perceived as slow in reaching beneficiaries. This study aims to develop a web-based information system for social assistance distribution that utilises fingerprint biometrics for recipient verification as a replacement for E-KTP, and incorporates a photo documentation feature with timestamps to record the time and location of distribution activities. The method used in this research is Research and Development (R&D). The novelty of this study lies in the integration of fingerprint authentication, photo timestamp evidence, and web-based monitoring within a single system for social assistance distribution. The results show that the developed system can validate recipient identities using fingerprints, provide timestamped photo evidence, support monitoring of distribution activities, and enhance transparency and efficiency in line with the government’s digitalisation programme.
EFFICIENT MRI-BASED BRAIN TUMOR CLASSIFICATION USING PRUNED SQUEEZENET ARCHITECTURE Ade Ismiaty Ramadhona Ht Barat; Poningsih Poningsih; Anjar Wanto
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.7963

Abstract

Brain tumors are among the most serious neurological diseases, requiring accurate diagnosis to support effective treatment. Magnetic Resonance Imaging (MRI) is widely used for brain tumor detection because it provides detailed visualization of brain structures. However, manual MRI interpretation is time-consuming and highly dependent on radiologists' expertise, potentially leading to inconsistent diagnoses. This study evaluates the performance of several deep learning architectures, including VGG16, DenseNet121, Custom CNN, and SqueezeNet, for multiclass brain tumor classification using MRI images. To address the computational limitations of deep neural networks in resource-constrained medical environments, a structured pruning approach based on polynomial decay sparsity scheduling was applied to the SqueezeNet model to reduce model complexity while preserving predictive performance. Experiments were conducted on a multiclass MRI dataset consisting of glioma, meningioma, pituitary tumor, and non-tumor images. The proposed pruned SqueezeNet achieved a classification accuracy of 98.70% and an AUC of 0.998, while reducing the model size to 2,970 KB and achieving an inference time of 105.40 ms. These results demonstrate that structured pruning effectively improves computational efficiency without significantly compromising classification accuracy, making the model suitable for deployment in resource-limited medical settings. Nevertheless, further validation using larger and multi-institutional MRI datasets is required before clinical implementation
COMPARATIVE BENCHMARKING OF YOLO11 FOR UAV-BASED HUMAN DETECTION IN SIMULATED DISASTER SCENARIOS A. Ahmad Fadil; Jumadi Mabe Parenreng; Muhammad Fardan; Muhammad Fajar B; Ana Sulistiana Alwi
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.8002

Abstract

Search and Rescue (SAR) operations require rapid and reliable identification of survivors in disaster-affected areas. This study presents an empirical benchmark of YOLO11m for UAV-oriented human detection in simulated disaster scenarios. The model was trained and evaluated using the synthetically generated C2A: Human Detection in Disaster Scenarios dataset and compared with YOLOv8m, YOLOv9m, and YOLOv10m under consistent training configurations. The experiments were conducted at a resolution of 640 × 640 pixels using mixed-precision training on dual NVIDIA T4 GPUs. YOLO11m achieved an mAP@50 of 0.850, an mAP@50–95 of 0.612, a Precision of 0.880, a Recall of 0.799, and a peak F1-score of 0.830 at a confidence threshold of 0.376. The model also recorded an average inference latency of 5.5 ms per image in the test environment. Compared with the evaluated medium-scale YOLO variants, YOLO11m achieved the highest mAP@50–95 while maintaining moderate parameter and computational requirements. These results indicate that YOLO11m provides a promising accuracy–efficiency baseline for UAV-based SAR research. However, because the evaluation relies on synthetic data and does not include onboard inference or physical UAV field trials, further validation using real-world aerial disaster imagery is required before operational deployment.
SENTIMENT ANALYSIS OF TWITTER (X) RESPONSES USING NAÏVE BAYES: A CASE STUDY OF JUMBO: SENTIMENT ANALYSIS Nurasiah; Latifah Nur Zam Zami; Yunianto Agung Nugroho
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.8037

Abstract

The rapid growth of social media platforms, especially Twitter (now rebranded as X), has made it a rich source for public opinion mining. This study focuses on analyzing public sentiment toward the animated “film Jumbo" by applying the Naïve Bayes Classifier algorithm to Twitter data. The research involves collecting tweets related to the film, preprocessing the data by removing noise such as stopwords, user mentions, and special characters, and then classifying sentiments into positive, negative, and neutral categories. The Naïve Bayes algorithm was chosen due to its effectiveness and efficiency in text classification tasks such as sentiment analysis. The classifier is trained on a labeled dataset and evaluated through performance metrics including accuracy, precision, recall, and F1-score. The results demonstrate that the Naïve Bayes Classifier can effectively capture public sentiment on social media, providing insights into audience reception of the “film Jumbo." Moreover, this research highlights the importance of integrating machine learning techniques with social media analytics for real-time sentiment monitoring. The model achieved an accuracy of 77% in classifying sentiments. Analysis results indicate that positive sentiment dominates public opinion, with a precision of 88% and recall of 83%, followed by negative sentiment with precision and recall of 75% and 71%, respectively, and neutral sentiment with precision of 40% and recall of 57%. These findings offer valuable insights for the film industry to better understand audience perceptions and make informed decisions.
ELIMINATING THE QUALITY PARADOX IN VIZWIZ CAPTIONING VIA DATA-CENTRIC CURATION AND PEFT LORA Rhama Rangga Dhiputra; Anna Baita
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.8060

Abstract

Vision-language models could be very useful for assistive technology, but they struggle significantly with processing low-quality, noisy photos that visually impaired individuals often take. The primary contribution of this research is a data-centric pipeline that combines Fast Fourier Transform (FFT) blur filtering with Parameter-Efficient Fine-Tuning (PEFT) utilizing Low-Rank Adaptation (LoRA) to directly confront and eradicate the “Quality Paradox” bias in accessibility datasets like VizWiz. We use the AdamW optimizer for memory-efficient training and perform comprehensive statistical ablation studies with FFT-based tertile splits to see how image quality affects the results. The optimized model achieves a CIDEr score of 0.4481, a strong BERTScore F1 of 0.8815, and a BLEU-4 of 0.0511. Statistical analysis (p = 0.622, Cohen’s d = -0.038) shows that this bias has been successfully removed, which means that performance is balanced on both severely blurry and crisp images. Further qualitative testing shows that the model can recognize text and objects even in very low light without needing an extra OCR module, demonstrating its viability as a stand-alone navigational aid.
IMPLEMENTATION OF DEVOPS APPROACH USING CI/CD WITH A SHARED-PIPELINE TO ACCELERATE WEB SERVICE DEVELOPMENT Ahmad Lukman Hakim; Diah Aryani; Daniati Uki Eka Saputri
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.8208

Abstract

The development of microservices-based web service applications requires fast, consistent, and automated integration and deployment processes. However, in practice, many organizations still rely on manual procedures and non-standardized pipeline configurations, which lead to release delays and increase the risk of operational errors. The DevOps approach through Continuous Integration and Continuous Delivery (CI/CD) has emerged as a relevant solution. Nevertheless, its practical implementation still requires clear and reusable guidance. This study aims to implement DevOps approach using CI/CD practices for the backend microservices at JEL Tech Inc by leveraging GitLab and a shared-pipeline scheme. The research adopts an applied research methodology with a case study approach, following the stages of the DevOps lifecycle, including plan, code, build, test, release, deploy, operate, and monitor. Pipeline automation is constructed using modular shell scripts executed by GitLab Runner and integrated with Docker, a Container Registry, and Kubernetes. The results demonstrate that the implementation of a shared-pipeline successfully standardizes build, package, and deployment processes across multiple microservices repositories. The implementation results show measurable improvements, including up to 90% reduction in deployment time, 400% increase in release frequency, and significant reduction in failure rates. This study contributes a reusable shared-pipeline architecture that extends existing DevOps implementation practices by providing a standardized, modular, and testable CI/CD model for microservices environments.
SARCASM DETECTION IN PALEMBANG LANGUAGE USING HYBRID CLASSICAL AND DEEP LEARNING APPROACHES Johannes Petrus; Antonius Wahyu Sudrajat; Muhammad Rachmadi
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.8222

Abstract

Research on sarcasm detection in sentences generally focuses on English and the national languages of certain countries, so that regional languages such as Palembang are still underrepresented in NLP research. This study aims to classify sarcasm in Palembang sentences by applying 12 models and evaluating their performance using a dataset containing 1,952 manually annotated samples. The experiment was also conducted using a 5-fold cross-validation scheme, and the statistical significance of the test results was analyzed using the Friedman t-test ( =41.96, FF=12.90). Contrary to common expectations, the Ensemble classifier achieved the best overall performance, attaining a mean F1-score of 0.877 and outperforming larger pre-trained and dialect-specific models. Even though it is still in the same language family, MelayuBERT's performance is very far behind (F1:0.691). Furthermore, the relatively lower performance of IndoBERT-1.5G (0.731) suggests that model scale alone does not guarantee effectiveness in low-resource language settings. These findings highlight the robustness of feature-engineered classical models compared to large-scale or dialect-specific pre-trained models for sarcasm detection in low-resource regional languages. Our research results with datasets sourced from varied domains have exceeded several national benchmarks. This study can be a baseline for further research.
IMPROVING LONG-TAIL RECOMMENDATION VIA ROULETTE WHEEL SELECTION USING HYBRID RATING AND TEMPORAL DECAY WEIGHTING Andy Maulana Yusuf; Miftah Farid Adiwisastra; Faizal Riza; Musrinah
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 12 No. 1 (2026): JITK Issue August 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v12i1.8240

Abstract

The phenomenon of information overload on digital platforms frequently leads to a skewed long-tail distribution, where user interactions concentrate on popular items while the majority remains undiscovered. This popularity bias is particularly acute in the book domain, where metaphorical titles defy traditional lexical matching, causing unique content to remain hidden in the long-tail area. While semantic models improve relevance, a significant research gap persists in mitigating the trade-off between accuracy and catalog exposure. This study proposes a novel stochastic framework by integrating Roulette Wheel Selection with hybrid rating and temporal decay weighting to enhance long-tail discoverability. To evaluate its generalizability, this mechanism was tested on the Goodreads Poetry dataset across four distinct content-based embedding models: SBERT-Tuned, SBERT, FastText, and Word2Vec. We conducted a rigorous comparative analysis between the proposed Stochastic (S) approach and Deterministic (D) Top-N selection. Experimental results demonstrate that the stochastic mechanism consistently improves catalog diversity across all baselines. SBERT-Tuned emerged as the most promising model, achieving a 461.71% increase in Catalog Coverage with a marginal 2.15% Recall reduction. Other models also exhibited significant gains, where the integration of Roulette Wheel Selection boosted coverage by 381.72% for FastText and 225.15% for Word2Vec, highlighting the framework's robustness. Furthermore, a consistent decrease in the Gini-index and an improvement in Novelty scores (ranging from +16% to +29%) confirm a more equitable distribution of item visibility. This research contributes a methodological advancement by proving that stochastic selection, guided by time-aware weighting, can effectively dismantle popularity bias without sacrificing relevance.

Page 52 of 55 | Total Record : 543

 50   51   52   53   54 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol. 12 No. 1 (2026): JITK Issue August 2026 Vol. 11 No. 4 (2026): JITK Issue May 2026 Vol. 11 No. 3 (2026): JITK Issue February 2026 Vol. 11 No. 2 (2025): JITK Issue November 2025 Vol. 11 No. 1 (2025): JITK Issue August2025 Vol. 10 No. 4 (2025): JITK Issue May 2025 Vol. 10 No. 3 (2025): JITK Issue February 2025 Vol. 10 No. 2 (2024): JITK Issue November 2024 Vol. 10 No. 1 (2024): JITK Issue August 2024 Vol. 9 No. 2 (2024): JITK Issue February 2024 Vol. 9 No. 1 (2023): JITK Issue August 2023 Vol. 8 No. 2 (2023): JITK Issue February 2023 Vol. 8 No. 1 (2022): JITK Issue August 2022 Vol 8 No 1 (2022): JITK Issue August 2022 Vol 7 No 2 (2022): JITK Issue February 2022 Vol 7 No 1 (2021): JITK Issue August 2021 Vol 6 No 2 (2021): JITK Issue February 2021 Vol 6 No 1 (2020): JITK Issue August 2020 Vol 5 No 2 (2020): JITK Issue February 2020 Vol 5 No 1 (2019): JITK Issue August 2019 Vol 4 No 2 (2019): JITK Issue February 2019 Vol 4 No 1 (2018): JITK Issue August 2018 Vol 3 No 2 (2018): JITK Issue February 2018 Vol 3 No 1 (2017): JITK Issue August 2017 Vol 2 No 2 (2017): JITK Issue February 2017 Vol 2 No 1 (2016): JITK Issue August 2016 More Issue