cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Hindarto
Contact Email
joincs@umsida.ac.id
Phone
+6282336441637
Journal Mail Official
joincs@umsida.ac.id
Editorial Address
https://joincs.umsida.ac.id/index.php/joincs/about/editorialTeam
Location
Kab. sidoarjo,
Jawa timur
INDONESIA
JOINCS (Journal of Informatics, Network, and Computer Science)
Published by Universitas Muhammadiyah Sidoarjo
ISSN : -     EISSN : 25415123     DOI : https://doi.org/10.21070/joincs
Core Subject : Science,
Computer Science & IT
JOINCS publishes original research papers in computer science and related subjects in system science, with consideration to the relevant mathematical theory. Applications or technical reports oriented papers may also be accepted and they are expected to contain deep analytic evaluation of the proposed solutions. JOINCS also welcomes research contributions on the traditional subjects such as : Theory of automata, algorithms and its complexity. But not limited to contemporary subjects such as: • Big Data • Internet of thing (IoT) • Parallel & distributed computing • Computer networks and its security • Neural networks • Computational learning theory • Database theory & practice • Computer modelling of complex systems • Decentralized Systems • Information Management in the Enterprise Context • Database related technical solutions for Information Quality • Information Quality in the context of Computer Science and Information Technology • Game Techology • Information System
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 88 Documents
 5   6   7   8   9 
Federated Learning for Privacy-Preserving Big Data Analytics in Distributed Systems: Federated Learning for Privacy-Preserving Big Data Analytics in Distributed Systems Ahmed Gheni Dawood; Ekhlas Muthanna Turki
JOINCS (Journal of Informatics, Network, and Computer Science) Vol. 9 No. 1 (2026): April
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/joincs.v9i1.1699

Abstract

Federated Learning (FL) is an important concept in big data analytics because it has changed the way collaborative model training can be done on devices that are decentralized while ensuring user privacy, an essential requirement in an accurate evidence-based and regulated environment with even stricter requirements from regulations like GDPR, HIPAA, CCPA and future laws on data sovereignty. This paper analyzed FL in depth. It described foundational concepts, architectural approaches, algorithmic approaches, real-world and practical applications and challenges in distributed systems. Key issues such as communication overhead, data heterogeneity, security risks, fairness, scalability, energy efficiency and compliance with regulations were also discussed and analyses were provided on any underpinning implications on FL performance. Seven tables provide comprehensive overviews of the algorithms, datasets, metrics of performance and applications, while nine figures in unique styles visualize trends, comparisons and data analytics to aid readability. Applications were provided in healthcare, IoT, financial sectors, smart cities and autonomous systems which lend evidence to the promise of FL as a revolutionary technology for privacy-respecting related analytics. Future directions for integrating FL highlights potential synergies with emergent technology such as quantum computing, blockchain, edge artificial intelligence and federated generative models, with supported rationales and inferences when necessary. This work provides a comprehensive and definitive reference point to enhance the scope and level of enquiry for researchers and practitioners who are trying to advance the development of distributed machine learning in sensitive situations to ultimately support the emergence of secure, scalable, ethical, and privacy-preserving analytics, which can drive future paradigm shifts
Development of an Automated Attendance System Based on Facial Recognition Using Convolutional Neural Networks (CNN) for Kaca Super Jaya MSME: Pengembangan Sistem Kehadiran Otomatis Menggunakan Pengenalan Wajah Menggunakan Convolutional Neural Network (CNN) terhadap UMKM Kaca Super Jaya Syaeful Anas Aklani; Jetset; Suwarno Suwarno
JOINCS (Journal of Informatics, Network, and Computer Science) Vol. 9 No. 1 (2026): April
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/joincs.v9i1.1692

Abstract

Attendance management is a critical component of human resource administration, yet conventional methods such as manual sign-in sheets and card-based systems are often inefficient, error-prone, and vulnerable to manipulation. This study aims to design and implement an automatic attendance system based on face recognition using Convolutional Neural Networks (CNN) for UMKM Kaca Super Jaya. The proposed system replaces manual attendance by enabling real-time, contactless, and automated attendance recording through facial identification. An applied research approach with qualitative methods was employed, involving system development, direct observation, and structured interviews with users. The CNN model was trained using facial image datasets under various conditions, including different lighting levels, facial expressions, and viewing angles, to improve robustness and accuracy. The system architecture integrates a camera as input, a CNN-based face recognition model, a backend server, and a web-based dashboard for attendance monitoring and reporting. Experimental results show that the system achieved an average face recognition accuracy of 96%, demonstrating reliable performance even under suboptimal lighting and non-frontal face angles. The implementation significantly reduced attendance processing time, minimized human error, and lowered the potential for fraudulent practices such as proxy attendance. These findings indicate that CNN-based face recognition is an effective and practical solution for enhancing attendance management efficiency and accuracy in small and medium enterprises.
Comparison of Naive Bayes and KNN for Honey-Mumford Learning Style Classification in Interpersonal Skill: Komparasi Naive Bayes dan KNN untuk Klasifikasi Gaya Belajar Honey-Mumford pada Interpersonal Skill Hari Moerti; Hamzah Setiawan
JOINCS (Journal of Informatics, Network, and Computer Science) Vol. 8 No. 2 (2025): November
Publisher : Universitas Muhammadiyah Sidoarjo

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

Abstract

Developing soft skills competence, particularly interpersonal abilities, often presents a challenge for Informatics students accustomed to technical and structured thinking patterns. The mismatch between teaching methods and student learning preferences can hinder the absorption of non-technical material. This study aims to classify student learning style profiles in the Interpersonal Skill course using a Machine Learning approach based on the Honey-Mumford model (Activist, Reflector, Theorist, Pragmatist). The research methodology employs Educational Data Mining techniques by comparing the performance of Naive Bayes and K-Nearest Neighbor (KNN) algorithms in predicting learning styles based on academic history data and behavioral questionnaires. Experimental results indicate that the Naive Bayes algorithm outperforms KNN in recognizing student characteristic patterns, achieving an accuracy rate of 93.33%. These findings suggest that engineering students possess heterogeneous learning styles; therefore, adaptive and varied teaching strategies are essential to optimize the comprehension of soft skills materia.
Website-Based Digitalization of the Expertise System (SiPAKAR) for Engineering Faculty Lecturers to Support SDGs 8 and 9: Digitalisasi Sistem Kepakaran (SiPAKAR) Dosen Fakultas Teknik Berbasis Website untuk Mendukung SDGs 8 dan 9 Yeni Yulianti; Nur Riska; Ahmad Lubi; Shilmi Arifah; Ali Idrus; Sri Sundari
JOINCS (Journal of Informatics, Network, and Computer Science) Vol. 8 No. 2 (2025): November
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/joincs.v8i2.1694

Abstract

Study This aim develop system the expertise of the lecturers of the Faculty of Engineering, Universitas Negeri Jakarta (SiPAKAR) is web- based for make things easier search and mapping skill lecturer based on field knowledge, publications, and experience research. Development system use Research and Development (R&D) method with the Waterfall model and algorithm TextRank in keyword extraction​ publication. Research results show that system capable integrate data from Google Scholar, SISTER, and ORCID automatic. Data analysis using statistics descriptive for evaluate level validity and satisfaction TKT users in research This is at level 4-6 which is development system expertise in environment limited, including expert data processing lecturer from internal source. Validation test by experts produce level 'Very Adequate' eligibility (89%), and response users show satisfaction by 85%. SiPAKAR expected support transparency academic, collaboration research, and achievement of SDGs No. 8 (Decent Work and Growth) Economy) and No. 9 (Industry, Innovation, and Infrastructure). Although not yet perfect and still face obstacles, systems This is step strategic For strengthen the link between lecturers, expertise, and collaboration industry-academic. So that the impact more wide achieved, necessary supported by policies, incentives, technology and systematic monitoring.
FIFO Method for Optimizing Pharmaceutical Inventory Management at the Pharmaceutical Installation Unit of the Pekalongan District Health Office: Metode FIFO Untuk Optimasi Pengelolaan Persediaan Obat Di Upt Instalasi Farmasi Dinas Kesehatan Kabupaten Pekalongan Mohamad Irsyad Mutaqin; Dewi Handayani Untari Ningsih
JOINCS (Journal of Informatics, Network, and Computer Science) Vol. 9 No. 1 (2026): April
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/joincs.v9i1.1706

Abstract

Abstract. Effective drug inventory management is crucial for ensuring drug availability and ensuring smooth healthcare services. The Pekalongan District Health Office's Pharmacy Installation Unit (UPT) still faces challenges in inventory management due to the use of a semi-computerized Microsoft Excel-based system that can potentially lead to recording errors, difficulty monitoring stock, and delays in reporting. Based on drug inventory data from January to December 2025, the number of incoming drugs was 10,964,906 and outgoing drugs was 20,460,686, with a difference of 9,495,780 and a distribution ratio of 186.6%, indicating an imbalance between drug receipts and expenditures and potential pressure on stock availability. This study aims to optimize drug inventory management through the application of the First In First Out (FIFO) method, a method that prioritizes drug expenditure based on the order of receipt. The research method used is descriptive with analysis of available drug inventory data. The results show that the application of the FIFO method can improve orderly stock management, minimize the risk of expiration, and improve the accuracy of recording and reporting. Thus, the FIFO method can be an effective solution in improving the efficiency and effectiveness of drug inventory management. Keywords: FIFO, Drug Inventory, Inventory Management, Pharmaceutical Installation, Optimization. Abstrak. Pengelolaan persediaan obat yang efektif sangat penting dalam menjamin ketersediaan obat dan kelancaran pelayanan kesehatan. UPT Instalasi Farmasi Dinas Kesehatan Kabupaten Pekalongan masih menghadapi kendala dalam pengelolaan persediaan karena penggunaan sistem semi komputerisasi berbasis Microsoft Excel yang berpotensi menimbulkan kesalahan pencatatan, kesulitan monitoring stok, dan keterlambatan pelaporan. Berdasarkan data persediaan obat periode Januari hingga Desember 2025, jumlah obat masuk sebesar 10.964.906 dan obat keluar sebesar 20.460.686, dengan selisih 9.495.780 serta rasio distribusi mencapai 186,6%, yang menunjukkan ketidakseimbangan antara penerimaan dan pengeluaran obat serta potensi tekanan terhadap ketersediaan stok. Penelitian ini bertujuan mengoptimalkan pengelolaan persediaan obat melalui penerapan metode First In First Out (FIFO), yaitu metode yang mengutamakan pengeluaran obat berdasarkan urutan waktu masuk. Metode penelitian yang digunakan adalah deskriptif dengan analisis terhadap data persediaan obat yang tersedia. Hasil penelitian menunjukkan bahwa penerapan metode FIFO mampu meningkatkan ketertiban pengelolaan stok, meminimalkan risiko kadaluarsa, serta meningkatkan akurasi pencatatan dan pelaporan. Dengan demikian, metode FIFO dapat menjadi solusi yang efektif dalam meningkatkan efisiensi dan efektivitas pengelolaan persediaan obat. Kata Kunci: FIFO, Persediaan Obat, Manajemen Persediaan, Instalasi Farmasi, Optimasi
Identification of Bengawan Solo River Water Quality Patterns Using K-Means Clustering Based on Physicochemical and Environmental Parameters: Identifikasi Pola Kualitas Air Sungai Bengawan Solo Menggunakan Klasterisasi K-Means Berdasarkan Parameter Fisik-Kimia dan Lingkungan Widya Cholid Wahyudin; Tole Sutikno; Rusydi Umar; Widya Cholid Wahyudin
JOINCS (Journal of Informatics, Network, and Computer Science) Vol. 9 No. 1 (2026): April
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/joincs.v9i1.1710

Abstract

Abstract. River water quality needs to be monitored continuously because changes in physicochemical and environmental parameters may indicate early changes in aquatic conditions. This study aims to identify water quality patterns in the Bengawan Solo River using K-Means clustering based on physicochemical and environmental parameters. The dataset consists of 1,753 field observations with attributes including temperature, pH, electrical conductivity, total dissolved solids, water color, odor, and weather condition. The research stages include feature selection, data preprocessing, categorical encoding, Z-score standardization, K-Means clustering, and cluster number evaluation. The number of clusters was tested from K=2 to K=5. Cluster quality was evaluated using Silhouette Score, Davies-Bouldin Index, Calinski-Harabasz Score, and Inertia. After data cleaning, 1,751 observations were used in the clustering process. The evaluation results show that K=2 is the best cluster number, with a Silhouette Score of 0.187638 and a Calinski-Harabasz Score of 456.873808. The clustering results formed two main patterns, namely Cluster 0 with 840 observations or 47.97% and Cluster 1 with 911 observations or 52.03%. Based on average parameter characteristics, Cluster 0 has higher electrical conductivity and TDS values than Cluster 1; therefore, it is interpreted as a higher water quality risk pattern. These results indicate that K-Means can identify initial water quality patterns in an unlabeled Bengawan Solo River dataset.
From Scalability to Sustainability: A 20-Year Retrospective on Deep Learning and Parameter-Efficient Fine-Tuning for Text Classification: Dari Skalabilitas ke Keberlanjutan: Tinjauan 20 Tahun tentang Pembelajaran Mendalam dan Penyesuaian Parameter yang Efisien untuk Klasifikasi Teks Andry Rachmadany; Ika Safitri Windiarti
JOINCS (Journal of Informatics, Network, and Computer Science) Vol. 9 No. 1 (2026): April
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/joincs.v9i1.1711

Abstract

In the area of natural language processing (NLP), especially regarding text classification, earlier methods that relied on traditional machine learning are being increasingly replaced by neural network designs like convolutional neural networks and recurrent neural networks. Additionally, the rise of transformer-based models has led to considerable improvements in performance, though this comes with higher demands for computing power and energy usage. This paper provides a look back at the development of deep learning and Parameter-Efficient Fine-Tuning (PEFT) methods for text classification from 2005 to 2025. The research explores important technological advancements, evaluates the balance between performance, scalability, and efficient computing, and points out the rising concern for sustainability in the development of artificial intelligence. The findings show a transition from strategies aimed at simply increasing scale to those that focus on more efficiency. In this setting, PEFT has become an important advancement in easing the computing load without greatly impacting performance, although it still faces challenges in flexibility and energy consciousness. These insights are anticipated to lay the groundwork for more research into creating environmentally friendly NLP technologies.
Context-Aware Transformer-Based Model for Aspect-Based Sentiment Analysis: A Systematic Literature Review: Model Berbasis Transformer yang Sadar Konteks untuk Analisis Sentimen Berbasis Aspek: Tinjauan Literatur Sistematis Moch. Fauzan; Ika Safitri Windiarti
JOINCS (Journal of Informatics, Network, and Computer Science) Vol. 9 No. 1 (2026): April
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/joincs.v9i1.1712

Abstract

Aspect-Based Sentiment Analysis (ABSA) is a critical natural language processing task aimed at identifying specific aspects within text and determining the sentiment polarity toward each aspect. Transformer-based models, particularly BERT and its variants, have demonstrated significant advances in ABSA through powerful contextual representations. However, challenges in capturing target-specific context and managing inter-subtask dependencies remain. This Systematic Literature Review (SLR) identifies, evaluates, and synthesizes current research on context-aware transformer models for ABSA, with emphasis on context-aware mechanisms, multi-task learning approaches, and BERT-family models. Following the PRISMA 2020 protocol, a structured search was conducted on the Scopus database using three Boolean queries, yielding 851 initial records. After deduplication (n=70), title/abstract screening (n=554 excluded), retrieval (n=147 not retrieved), and full-text eligibility assessment (n=48 excluded), 32 studies were included for synthesis. Three primary model categories were identified: (1) BERT baselines establishing strong end-to-end ABSA performance; (2) context-aware variants employing context-guided attention (CG-BERT, QACG-BERT, LCF-ATEPC, cascade models); and (3) multi-task transformers (BERT-MTL, RoBERTa-MTL, MTL-AraBERT, SABKG, MLEGCN) handling ABSA subtasks jointly. Reported F1-scores ranged from 50–89% across SemEval-2014/2015/2016 and domain-specific datasets. ntext-aware and multi-task transformer models represent the state of the art in ABSA. Open challenges include implicit aspect handling, cross-domain generalization, model efficiency, and evaluation of large generative language models (LLMs) for fine-grained sentiment tasks.

Page 9 of 9 | Total Record : 88

 5   6   7   8   9 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol. 9 No. 1 (2026): April Vol. 8 No. 2 (2025): November Vol. 8 No. 1 (2025): April Vol. 7 No. 2 (2024): November Vol. 7 No. 1 (2024): April Vol. 6 No. 2 (2023): November Vol. 6 No. 1 (2023): April Vol. 5 No. 2 (2022): November Vol 5 No 1 (2022): April Vol. 4 No. 2 (2021): November Vol 4 No 1 (2021): April Vol. 3 No. 2 (2020): November Vol 3 No 2 (2020): November Vol 3 No 1 (2020): April Vol 2 No 2 (2019): November Vol 2 No 1 (2019): April Vol. 2 No. 1 (2019): April Vol 1 No 1 (2017): April More Issue