Claim Missing Document
Check
Articles

Found 29 Documents
Search

Implementasi dan Manajemen State Pada Website Next.js: Perbandingan Context API dan Redux Pada Website Mangaice Wisnu Shena Arrafi; Putra, Ricky Eka
Journal of Informatics and Computer Science (JINACS) Vol. 6 No. 04 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jinacs.v6n04.p1131-1144

Abstract

Abstrak—Pengelolaan state yang efisien menjadi tantangan dalam pengembangan website modern terutama ketika website memiiki tingkat kompleksitas yang tinggi. Pemillihan tools yang tepat dalam memanajemen state sering kali menimbulkan kebingungan bagi developer, mengingat masing-masing tools memiliki pendekatan yang berbedan dan keunggulan serta kekurangan masing-masing dalam hal performa, skalabilitas, dan memori. Contoh tools yang populer digunakan dalam manajemen state adalah Context API dan Redux. Oleh karena itu, penelitian ini mengimplementasikan dan melakukan perbandingan terhadap Context APi dan Redux pada website Mangaice yang dikembangkan dengan menggunakan framework Next.js. Perbandingan dilakukan berdasarkan parameter performa, skalabilitas, dan memori. Penelitian ini diharapkan dapat menjadikan panduan empiris dalam memilih state management tools yang sesuai dengan kebutuhan projek. Penelitian dilakukan dengan tahapan yang pertama adalah studi literatur, analisis kebutuhan, implementasi, dan pengujian. Pengujian dalam penelitian dilakukan dengan menjalankan skenario penggunaan yang mencangkup autentikasi, pencarian dan penambahan library, membaca manga dan penyimpanan progress baca, pengelolaan history baca, dan pengaturan preferensi pengguna. Dari hasil pengujian, didapatkan hasil bahwa Redux unggul 11,16% dalam performa, terutama dalam menampilkan konten utama dan rendering pada repeat view, sedangkan Context API lebih efisien dalam scripting dan painting. Dari segi skalabilitas, Redux lebih unggul 25,91%, dengan waktu respons lebih cepat, throughput lebih tinggi, dan stabilitas lebih baik dalam skenario dengan banyak pengguna. Dalam penggunaan memori, Redux lebih efisien dengan penghematan total sebesar 51,0% dibandingkan Context API setelah adanya interaksi pengguna. Pada akses awal, Redux juga lebih hemat sekitar 3,5%.   Kata Kunci— Context API, Redux, Perbandingan State Management, Pengembangan Website.
Pengaruh Pengembangan Kapasitas, Mentoring Dan Motivasi Terhadap Pemberdayaan Sumber Daya Manusia Bidang Pariwisata Di Wilayah Kecamatan IV Koto Kabupaten Agam Putra, Ricky Eka; Hasan, Alizar
Jurnal Ekonomika Dan Bisnis (JEBS) Vol. 4 No. 4 (2024): Juli-Agustus
Publisher : CV. ITTC INDONESIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47233/jebs.v4i4.2027

Abstract

IV Koto District is one of the 16 sub-districts in Agam Regency which has 7 Nagari and 24 Jorong. The purpose of this research is to determine the role of the sub-district government in providing capacity development, mentoring and motivation in efforts to increase human resource empowerment in the tourism sector in the IV Koto sub-district area, Agam Regency. The population in the study was the entire Nagari Subdistrict IV Koto, Agam Regency, totaling 156 people. Samples were searched using the Slovin formula, resulting in a sample of 61 people. The data analysis technique uses SEM-PLS analysis. The research results show a positive and significant influence of capacity development on HR empowerment in the Nagari Sector IV Koto District, Agam Regency. There is a positive and insignificant influence of mentoring on HR empowerment in the Nagari Sector IV Koto District, Agam Regency. There is a positive and significant influence of motivation on HR empowerment in the Nagari Sector IV Koto District, Agam Regency.
A Systematic Literature Review on Chatbot Development For Whatsapp: Programming Language, Method, And Utility Rahulil, Muhammad; Yuni Yamasari; Ricky Eka Putra; I Made Suartana; Anita Qoiriah
Jurnal Serambi Engineering Vol. 10 No. 3 (2025): Juli 2025
Publisher : Faculty of Engineering, Universitas Serambi Mekkah

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

Abstract

The development of chatbot technology in recent years has shown rapid advancements across various sectors, particularly on popular communication platforms such as WhatsApp. A systematic review is necessary to identify advancements related to chatbot development on WhatsApp. Therefore, this study presents a systematic literature re-view on the development and use of WhatsApp chatbots using the PRISMA framework. From an initial search of 41 studies, followed by filtering according to categories, eight relevant articles were identified from various digital data-bases through focused searches using the keyword "WhatsApp chatbot". The review results indicate that Natural Language Processing (NLP) methods are the most commonly applied approach in chatbot development, with Python being the dominant programming language. This is attributed to Python's flexibility and strong library support, such as NLTK, spacy, and TensorFlow, which enable more efficient chatbot development. The findings reveal that WhatsApp chatbots have been applied in various sectors, including healthcare, business, and education. The study's outcomes highlight the challenges and opportunities in future chatbot development, such as the integration of additional features and the enhancement of conversational context understanding. By providing in depth insights into trends and best practices, this study contributes to the development of WhatsApp chatbots as increasingly relevant and effective automated communication tools.
Pelatihan Aplikasi Komputer untuk Penulisan Ilmiah di SMPN 1 Pagerwojo Tulungagung Jawa Timur: Computer Application Training for Scientific Writing at SMPN 1 Pagerwojo Tulungagung East Java Yamasari, Yuni; Qoiriah, Anita; Putra, Ricky Eka; Prihanto, Agus; Suartana, I Made; Prapanca, Aditya
PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat Vol. 10 No. 8 (2025): PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat
Publisher : Institute for Research and Community Services Universitas Muhammadiyah Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33084/pengabdianmu.v10i8.9435

Abstract

Teacher professionalism development is one of the strategic steps in improving the quality of education at SMP Negeri 1 Pagerwojo, Tulungagung, East Java. However, limited access to training and a lack of utilization of technology are significant obstacles for teachers, especially in the field of scientific writing. Scientific writing skills are essential in improving teaching skills, developing learning materials, and contributing to educational literature. To solve this problem, this community service activity aims to enhance teachers' skills in scientific writing through training in the use of applications. The training utilizes key features, such as reference management, automatic citation settings, and scientific document management. The training method includes the application installation stage, direct training, and analysis of results through measuring participant responses using a Likert scale. The study showed that the training improved teachers' understanding and skills in utilizing technology to support scientific writing. Most participants responded positively to the training, with a percentage of 77.55%. These results indicate that similar training needs to be further developed to support teacher professionalism, especially in areas with limited access to training.
CoAtNet for Chest X-Ray Report Generation with Bi-LSTM and Multi-Head Attention Akbar, Rafy Aulia; Putra, Ricky Eka; Yustanti, Wiyli
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 7 No. 4 (2025): November
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/ijeeemi.v7i4.271

Abstract

In clinical environments, Chest X-Ray (CXR) represents the most prevalent diagnostic instrument, particularly facilitating diagnostic procedures through medical report. However, manual report preparation is time-consuming, highly dependent on the expertise of radiologists, and carries the risk of errors due to high workloads and limited expert staff. Therefore, an automated system based on artificial intelligence is needed to ease the workload of radiologists while increasing consistency. This study aims to develop an automated medical report generation system with balanced data distribution, reliable encoder, and bidirectional contextual understanding. The main contributions of this study include the implementation of an undersampling strategy based on majority captions followed by oversampling on minority labels while maintaining a proportion of labels with higher frequencies, the use of Bi-LSTM with Multi Head Attention (MHA) to strengthen text context understanding, and the use of CoAtNet as a visual encoder that combines the strengths of CNN and Transformer. The methodology incorporates image preprocessing via gamma correction for contrast improvement, data selection, balancing through combined undersampling and oversampling, and CoAtNet implementation as encoder paired with Bi-LSTM and MHA as decoder. Experimental execution employed the IU X-ray dataset, with assessment conducted using BLEU and ROUGE-L metrics. Outcomes revealed that the CoAtNet configuration with Bi-LSTM and MHA, coupled with the undersampling-oversampling strategy, delivered superior performance evidenced by a cumulative score of 1.642, with BLEU-1 to BLEU-4 and ROUGE-L achieving 0.480, 0.329, 0.245, 0.183, and 0.405, respectively. These findings prove that the combination of data balancing strategies with CoAtNet and Bi-LSTM is able to produce more accurate automated medical reports and reduce bias towards the majority label.
Rule-Based Adaptive Chatbot on WhatsApp for Visual, Auditory, and Kinesthetic Learning Style Detection Rahulil, Muhammad; Yamasari, Yuni; Putra, Ricky Eka; Suartana, I made; Qoiriah, Anita
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 8 No 1 (2026): January
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v8i1.1215

Abstract

Adapting learning methods to individual learning styles remains a major challenge in digital education due to the static nature of traditional questionnaires and the absence of adaptive feedback mechanisms. This study aimed to develop a rule-based adaptive WhatsApp chatbot capable of automatically identifying users’ learning styles, visual, auditory, and kinesthetic, through a weighted questionnaire enhanced with probabilistic refinement. The proposed system introduces an adaptive decision framework that dynamically manages conversation flow using score dominance evaluation, early termination, and selective question expansion. Bayesian posterior probability estimation is employed to strengthen decision confidence in borderline cases, ensuring consistent and interpretable results even when user responses are ambiguous. The chatbot was implemented using WhatsApp-web.js and MongoDB, supported by session validation and activity log monitoring to ensure operational reliability and data integrity. System validation involved white-box testing using Cyclomatic Complexity to verify logical accuracy and 20-fold cross-validation using a Support Vector Machine (SVM) to evaluate classification performance. The adaptive model achieved an accuracy of 80.2% and an AUC of 0.902, supported by a balanced precision (0.738), recall (0.662), and F1-score (0.698). These results demonstrate stable discriminative capability and confirm that the adaptive scoring mechanism effectively reduces redundant questioning, lowers cognitive load, and improves interaction efficiency without compromising reliability. In conclusion, the study successfully achieved its objective of developing an adaptive, efficient, and mathematically transparent learning style detection system. The findings confirm that adaptive rule-based logic reinforced by probabilistic reasoning can significantly enhance the efficiency and reliability of digital learning assessments. Future research will extend this framework by incorporating multimodal behavioral indicators and personalized learning content to further strengthen adaptive learning support
Deep Learning-Based Detection of Online Gambling Promotion Spam in Indonesian YouTube Comments Ammar, Muhammad Zhafran; Putra, Ricky Eka; Yamasari, Yuni
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.11240

Abstract

Online gambling promotion has increasingly penetrated social media platforms, with YouTube comments becoming a frequent target for spam-based advertising. Such activities not only violate platform policies but also expose users to harmful content. Addressing this issue requires automated detection systems capable of handling noisy, informal, and highly imbalanced text data. This study investigates the effectiveness of four recurrent neural architectures LSTM, GRU, BiLSTM, and BiGRU for detecting gambling promotion comments in Indonesian YouTube data. To address class imbalance, multiple experimental scenarios were explored, including the original distribution, undersampling, oversampling, and class weighting. Model performance was evaluated using accuracy, precision, recall, F1-score, ROC-AUC, and confusion matrix analysis. The results show that bidirectional models outperformed their unidirectional counterparts, with BiGRU achieving the best overall performance. When combined with class weighting, BiGRU reached 98% accuracy, 0.83 F1-score, and 0.971 ROC-AUC, demonstrating a superior ability to detect minority-class instances. Oversampling improved recall substantially but increased false positives, while undersampling reduced accuracy; class weighting provided the most balanced performance across metrics. These findings confirm that BiGRU with class weighting offers the most practical balance between accuracy, recall, and computational efficiency, making it well-suited for real-time moderation systems. The study provides a strong foundation for future research on transformer-based architectures and cross-platform spam detection in Indonesian social media environments.
MD-ViT: Multidomain Vision Transformer Fusion for Fair Demographic Attribute Recognition Putri, Rezky Arisanti; Putra, Ricky Eka; Yamasari, Yuni
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p64-79

Abstract

Demographic attribute recognition particularly race and gender classification from facial images, plays a critical role in applications ranging from precision healthcare to digital identity systems. However, existing deep learning approaches often suffer from algorithmic bias and limited robustness, especially when trained on imbalanced or non-representative data. To address these challenges, this study proposes MD-ViT, a novel framework that leverages multidomain Vision Transformer (ViT) fusion to enhance both accuracy and fairness in demographic classification. Specifically, we integrate embeddings from two task-specific pretrained ViTs: ViT-VGGFace (fine-tuned on VGGFace2 for structural identity features) and ViT-Face Age (trained on UTKFace and IMDB-WIKI for age-related morphological cues), followed by classification using XGBoost to model complex feature interactions while mitigating overfitting. Evaluated on the balanced DemogPairs dataset (10,800 images across six intersectional subgroups), our approach achieves 89.07% accuracy and 89.06% F1-score, outperforming single-domain baselines (ViT-VGGFace: 88.61%; ViT-Age: 78.94%). Crucially, fairness analysis reveals minimal performance disparity across subgroups (F1-score range: 87.38%–91.03%; σ = 1.33), indicating effective mitigation of intersectional bias. These results demonstrate that cross-task feature fusion can yield representations that are not only more discriminative but also more equitable. We conclude that MD-ViT offers a principled, modular, and ethically grounded pathway toward fairer soft biometric systems, particularly in high-stakes domains such as digital health and inclusive access control.
Analisis Sentimen Pengguna X/Twitter Terhadap Timnas Sepakbola Indonesia di Era Shin Tae Yong dengan BERT&RNN Subroto, Jahfal Azzuhri; Ricky Eka Putra
Journal of Informatics and Computer Science (JINACS) Article In Press(1)
Publisher : Universitas Negeri Surabaya

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

Abstract

Abstrak— Perkembangan media sosial, khususnya Twitter (X), menjadikan platform ini sebagai ruang utama bagi masyarakat untuk mengekspresikan opini terhadap performa Timnas Sepakbola Indonesia di bawah kepelatihan Shin Tae Yong (STY). Penelitian ini bertujuan untuk menganalisis dan membandingkan performa empat model analisis sentimen berbasis kombinasi IndoBERT dan arsitektur Recurrent Neural Network (RNN), yaitu IndoBERT + RNN, IndoBERT + LSTM, IndoBERT + BiLSTM, dan IndoBERT + GRU. Data dikumpulkan menggunakan Tweet Harvest dan melalui tahapan preprocessing meliputi cleaning, case folding, normalisasi, tokenizing, stopword removal, stemming, serta labeling menggunakan InSet Lexicon yang kemudian divalidasi secara manual. Setiap model dilatih menggunakan beberapa konfigurasi hyperparameter, seperti variasi hidden size, batch size, dropout, learning rate, serta jumlah unit RNN untuk menemukan performa optimal pada tahap pelatihan dan validasi. Konfigurasi terbaik dari masing-masing model kemudian digunakan sebagai model final untuk dievaluasi pada skenario tiga label (positif, netral, negatif) dan dua label (positif, negatif). Evaluasi dilakukan menggunakan classification report dan confusion matrix. Hasil penelitian menunjukkan bahwa pada skenario tiga label, model IndoBERT+RNN memberikan performa terbaik dengan akurasi 0,69 dan Macro F1-Score 0,68. Sementara itu, pada skenario dua label, model IndoBERT+GRU menghasilkan performa tertinggi dengan akurasi dan Macro F1-Score sebesar 0,83. Temuan ini menegaskan bahwa pemilihan konfigurasi optimal pada kombinasi model berbasis transformer dan jaringan berulang berpengaruh signifikan terhadap peningkatan akurasi analisis sentimen berbahasa Indonesia. Kata Kunci— Analisis sentimen, IndoBERT, RNN, Twitter, Timnas Indonesia