Article Per Year (5 Year)
p-Index From 2021 - 2026
1.048
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Journal of Intelligent Computing and Health Informatics (JICHI) Djtechno: Jurnal Teknologi Informasi Journal of Computing Theories and Applications Proceeding of Informatics Collaborations and Dessimenation Meeting (Infocoding)
Dhendra Marutho
Universitas Muhammadiyah Semarang
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Electrical & Electronics Engineering Engineering Medicine & Pharmacology Public Health

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Robust Few Shot Biological Pathology Classification via Optimized Contrastive MobileNetV2: A Transferable Model for Low Resource Medical Imaging Nurul Adi Prawira; Muhammad Firmansyah; Dhendra Marutho; Achraf Ouhab
Journal of Intelligent Computing & Health Informatics Vol 7, No 1 (2026): March
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v7i1.20179

Abstract

Artificial intelligence has revolutionized computational diagnostics, however deploying reliable intelligent systems in extreme low-resource environments remains a critical structural challenge in health informatics. Conventional deep learning architectures, such as standard Convolutional Neural Networks (CNNs), are inherently data-hungry, making them prone to severe overfitting and catastrophic generalization failures when applied to rare biological pathologies. To overcome this limitation, we propose an Optimized Contrastive MobileNetV2 architecture embedded within a Few-Shot Learning (FSL) framework. By mathematically modifying the latent space representation using a contrastive loss function, the proposed model learns discriminative metric distances rather than relying on massive raw feature memorization. To rigorously validate the algorithm, we utilize a highly constrained dataset comprising merely 120 biological pathogen samples as a cross-domain proxy testbed, accurately simulating the extreme visual complexity and data scarcity typical of rare medical diagnostic scenarios. Extensive episodic evaluations demonstrate that the proposed methodology significantly outperforms conventional baselines. Under a 10-shot learning paradigm, the contrastive architecture achieved a macro-averaged accuracy of 89.2% and an F1-Score of 89.3%, remaining statistically robust against stochastic variations (p < 0.001). Furthermore, the integration of depthwise separable convolutions restricts the model complexity to approximately 3.4 × 10^6 parameters. Crucially, empirical evaluations confirm that this framework occupies merely 13.5 MB of physical storage and achieves an ultra-low inference latency of 12.5 ms per image. Ultimately, this study establishes a highly transferable, computationally efficient algorithmic model ready for seamless integration into intelligent clinical decision support systems and remote edge-computing health architectures.
Resource Efficient Semantic Retrieval Pipeline via Generative Captioning and Text-to-Text Transformers for Bridging the Modality Gap Muhammad Firmansyah; Dhendra Marutho; Irwansyah Saputra; Eleni Vogiatzi
Journal of Intelligent Computing & Health Informatics Vol 6, No 2 (2025): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v6i2.19240

Abstract

The rapid expansion of multimodal digital content necessitates the development of robust information retrieval systems capable of bridging the semantic gap between visual and textual data. However, contemporary cross- modal models, such as CLIP, impose significant computational demands, rendering them impractical for real-time deployment in resource-limited environments. To address this efficiency challenge, this study introduces a novel lightweight retrieval pipeline that reconceptualizes cross-modal retrieval as a text-to-text task through generative transformation. The proposed methodology employs the Bootstrapped Language-Image Pretraining (BLIP) model to distill visual features into rich textual descriptions, which are subsequently encoded into dense semantic vectors using the T5 transformer architecture. Extensive experiments conducted on the MSCOCO and Flickr30K datasets demonstrate that the proposed pipeline achieves a Semantic Average Recall (SAR@5) of 0.561, significantly surpassing traditional lexical (BM25) and dense (SBERT) baselines. Notably, while the computationally intensive CLIP model retains a slight advantage in absolute accuracy, our approach delivers approximately 90% of CLIP’s semantic performance while enhancing inference throughput by 2.1× and reducing GPU memory consumption by 62%. These findings confirm that generative semantic distillation offers a scalable, cost-effective alternative to end-to-end multimodal systems, particularly for latency-sensitive applications requiring high semantic fidelity.
HYBRID DEEP LEARNING RANDOM FOREST OPTIMASI PEMILIHAN FITUR UNTUK PREDIKSI CHURN INDUSTRI TELEKOMUNIKASI Atika Mutiarachim; Dhendra Marutho; Nur Atika Yuniarti; Ryan Arya Pramudya; Jaluanto Sunu Punjul Tyoso
Djtechno: Jurnal Teknologi Informasi Vol 6, No 2 (2025): Agustus
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/djtechno.v6i2.7052

Abstract

Customer churn merupakan tantangan kritis dalam industri telekomunikasi yang berdampak signifikan terhadap profitabilitas perusahaan. Penelitian ini mengusulkan pendekatan hybrid machine learning untuk memprediksi customer churn dengan mengintegrasikan deep learning dan random forest serta mengoptimalkan performa melalui seleksi fitur chi-square dan information gain. Dataset IBM Telco Customer Churn yang terdiri dari 7.043 sampel dengan 31 atribut digunakan dalam penelitian ini. Metodologi penelitian meliputi preprocessing data, implementasi 10-fold cross validation, aplikasi metode seleksi fitur, dan evaluasi performa menggunakan confusion matrix serta metrik klasifikasi biner. Hasil penelitian menunjukkan bahwa implementasi seleksi fitur secara signifikan meningkatkan akurasi prediksi, di mana akurasi tanpa seleksi fitur mencapai 97.00% (Deep Learning) dan 98.68% (Random Forest), sedangkan dengan seleksi fitur chi-square meningkat menjadi 97.97% (Deep Learning) dan 98.72% (Random Forest). Performa terbaik dicapai oleh kombinasi Random Forest dengan seleksi fitur information gain yang menghasilkan akurasi 98.75%, precision 98.37%, recall 99.96%, dan F-measure 99.16%. Temuan ini membuktikan efektivitas kombinasi algoritma ensemble dengan teknik seleksi fitur dalam mengoptimalkan prediksi customer churn untuk mendukung strategi retensi pelanggan yang lebih tepat sasaran
A Hybrid VADER–IndoBERT Framework for Robust Sentiment Analysis of Long and Ambiguous Indonesian Texts: Margareta Valencia Suci Handayani; Ruri Suko Basuki; Muljono; Raden Arief Nugroho; Dhendra Marutho; Yo Ceng Giap; Deshinta Arrova Dewi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 4 (2026): August 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i4.7377

Abstract

The rapid expansion of digital learning platforms has increased the reliance on user-generated reviews for service evaluation and quality monitoring. However, sentiment analysis of Indonesian reviews remains challenging due to the prevalence of long sentences, mixed sentiments, and ambiguous linguistic expressions. This study introduces a Hybrid VADER–IndoBERT framework designed to improve sentiment classification robustness on complex Indonesian texts. A dataset of 4,904 Ruangguru application reviews was collected through web scraping and processed using a hybrid pipeline consisting of preprocessing, translation-based silver-standard sentiment labeling with VADER, and class balancing via Random Oversampling (ROS). The IndoBERT classifier was evaluated against a Bidirectional Long Short-Term Memory (BiLSTM) baseline. Experimental results show that IndoBERT achieved 90.9% accuracy, outperforming BiLSTM at 86.4%, demonstrating the superiority of Transformer-based architectures in capturing long-range dependencies and handling ambiguous sentiment cues. These findings highlight the effectiveness of integrating lexicon-based and Transformer-based approaches to achieve more robust sentiment analysis on linguistically complex Indonesian texts.
Transformer-Based Support for Content-Validity Pre-Screening in Educational Materials Safuan Safuan; Dhendra Marutho; Ahmad Ilham; Muhammad Munsarif; Wendy Sarasjati; Edy Winarno; Arnold Adimabua Ojugo; De Rosal Ignatius Moses Setiadi
Journal of Computing Theories and Applications Vol. 4 No. 1 (2026): JCTA 4(1) 2026
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jcta.16829

Abstract

Content validity assessment is essential for determining whether educational materials adequately represent intended learning outcomes. However, conventional assessment procedures require substantial expert time and may produce inconsistent decisions across large item collections. This study develops a transformer-based framework to support content-validity pre-screening through two complementary tasks: predicting expert-derived Aiken’s V coefficients and classifying instructional-item essentiality. The final dataset comprised 652 Indonesian-language educational text items independently evaluated by four subject-matter experts. To reduce information leakage, identical and normalized-equivalent texts were grouped before applying a group-aware 70:15:15 training–validation–test split. Classical TF-IDF-based baselines were compared with IndoBERT, multilingual BERT, XLM-RoBERTa, and multilingual DeBERTa-v3. For Aiken’s V regression, multilingual BERT achieved the lowest MAE of 0.0501, the lowest RMSE of 0.0625, and the highest R² of 0.5239, whereas multilingual DeBERTa-v3 achieved the highest Spearman correlation of 0.7532. For essentiality classification, XLM-RoBERTa achieved the highest accuracy of 0.8557 and Macro-F1 of 0.8161, whereas multilingual BERT achieved the highest balanced accuracy of 0.8135 and ROC-AUC of 0.9111. Error analysis showed that the models captured textual patterns associated with expert-derived outcomes but remained limited when judgments depended on broader curricular context, competency hierarchies, prerequisite relationships, or relationships among instructional items. The findings support the use of transformer models as human-in-the-loop decision-support tools for prioritizing uncertain or potentially problematic educational items. However, the framework should be interpreted as a pre-screening mechanism rather than a replacement for expert judgment, and external validation across institutions and disciplines remains necessary.
Model Monitoring Jaringan dengan Notifikasi Real-time melalui Telegram Bot di Gedung GKB2 Universitas Muhammadiyah Semarang Akhmad Fathurohman; Dhendra Marutho; Muhammad Fachrur
Proceeding of Informatics Collaborations and Dessimenation Meeting Vol. 2 No. 1 (2026)
Publisher : Universitas Muhammadiyah Surakarta

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

Abstract

Upaya menjamin stabilitas konektivitas di era digital merupakan urgensi utama bagi ekosistem akademik terkhusus di Gedung GKB2 Universitas Muhammadiyah Semarang (Unimus) sebagai Gedung Utama Perkuliahan dan Pusat Laboratorium Komputer. Kodisi yang ada pengelolaan jaringan masih menggunakan monitoring konvensional yang relatif lambat, penelitian ini mengarsiteki solusi cerdas menggunakan The Dude MikroTik yang terintegrasi secara dinamis dengan Telegram Bot. Metode dalam penelitian ini adalah pendekatan Research and Development (R&D) model Waterfall. Sistem yang dirancang menciptakan alur kerja otomatis dengan dukunga tools Zapier dan Google Sheets, sebagai log yang mudah diolah dan divisualisasikan. Kesimpulan dari penelitian ini adalah bahwa sistem monitoring mencapai tingkat device discovery 100% dengan latensi deteksi gangguan hanya dalam 25–40 detik, sehingga memungkinkan untuk penanganan gangguan menjadi lebih cepat. Inovasi ini mentransformasi manajemen jaringan menjadi lebih proaktif, presisi, dan responsif terhadap dinamika gangguan.
Co-Authors Achraf Ouhab Ahmad Ilham Akhmad Fathurohman Arnold Adimabua Ojugo Atika Mutiarachim De Rosal Ignatius Moses Setiadi Deshinta Arrova Dewi Edy Winarno Eleni Vogiatzi Irwansyah Saputra Jaluanto Sunu Punjul Tyoso Margareta Valencia Suci Handayani Muhammad Fachrur Muhammad Firmansyah Muhammad Munsarif Muljono, - Nur Atika Yuniarti Nurul Adi Prawira Raden Arief Nugroho Ruri Suko Basuki Ryan Arya Pramudya Safuan Safuan Wendy Sarasjati Yo Ceng Giap