cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Yuhefizar
Contact Email
jurnal.resti@gmail.com
Phone
+628126777956
Journal Mail Official
ephi.lintau@gmail.com
Editorial Address
Politeknik Negeri Padang, Kampus Limau Manis, Padang, Indonesia.
Location
,
INDONESIA
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Published by Ikatan Ahli Informatika Indonesia
ISSN : 25800760     EISSN : 25800760     DOI : https://doi.org/10.29207/resti.v2i3.606
Core Subject : Science, Engineering,
Computer Science & IT Engineering
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) dimaksudkan sebagai media kajian ilmiah hasil penelitian, pemikiran dan kajian analisis-kritis mengenai penelitian Rekayasa Sistem, Teknik Informatika/Teknologi Informasi, Manajemen Informatika dan Sistem Informasi. Sebagai bagian dari semangat menyebarluaskan ilmu pengetahuan hasil dari penelitian dan pemikiran untuk pengabdian pada Masyarakat luas dan sebagai sumber referensi akademisi di bidang Teknologi dan Informasi. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) menerima artikel ilmiah dengan lingkup penelitian pada: Rekayasa Perangkat Lunak Rekayasa Perangkat Keras Keamanan Informasi Rekayasa Sistem Sistem Pakar Sistem Penunjang Keputusan Data Mining Sistem Kecerdasan Buatan/Artificial Intelligent System Jaringan Komputer Teknik Komputer Pengolahan Citra Algoritma Genetik Sistem Informasi Business Intelligence and Knowledge Management Database System Big Data Internet of Things Enterprise Computing Machine Learning Topik kajian lainnya yang relevan
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 1,185 Documents
 115   116   117   118   119 
DETR-CLIP-BLIP Integrated Framework for Context-Guided Multimodal Knowledge Graph Retrieval Raihan Atsal Hafizh; Kemas Rahmat Saleh Wiharja
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7647

Abstract

Image search systems that rely on metadata tags or basic captions often miss the semantic relationships and visual details needed for complex queries. This study presents a multimodal knowledge graph framework that combines DETR for object detection, CLIP for attribute classification across 188 dimensions, and BLIP for caption generation. On the COCO 2017 validation set (5,000 images), the pipeline processed 4,906 images successfully, of which 4,243 contained the multiple objects required for relationship extraction. The resulting knowledge graph reached 99.98% relational coverage among multi-object images and 2.94 relationships per image, with 117 of the 188 attributes appearing in the data. Retrieval was evaluated under a self-consistency protocol relevance defined by the system's own top-ranked matches yielding an MRR of 0.96 for keyword-based queries and 0.29 for relationship-based queries, with Recall@50 of 88% for the latter. The framework runs on pretrained models without task-specific training and produces both structured triples and human-readable descriptions, supporting applications such as visual question answering, scene understanding, and context-aware image retrieval.
Two-stage Transfer Learning for Chilli Leaf Disease Classification using CNN and Vision Transformer Rudi Kurniawan; Samsuryadi Samsuryadi; Fatma Susilawati Mohamad; Bunga Intan; Nelly Khairani Daulay
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7674

Abstract

Chili cultivation is considerably affected by leaf diseases, making timely and reliable disease identification essential for maintaining agricultural productivity. While deep learning has demonstrated strong capabilities in plant disease recognition, many existing studies primarily focus on modifying network architectures rather than optimizing the training process. This study introduces a two-stage transfer learning framework that combines frozen-backbone adaptation with controlled fine-tuning to enhance classification performance. The experiments utilized a publicly available dataset comprising 12,000 augmented chili leaf images representing six disease categories. Several deep learning architectures were investigated, including DenseNet121, EfficientNetB0, MobileNetV2, ResNet152V2, and the Vision Transformer (ViT-B16). The experimental results indicate that the proposed two-stage training strategy improves classification performance consistently across the evaluated architectures. Among the models, ViT-B16 obtained the highest test accuracy of 99.61%, together with stable macro-averaged precision, recall, and F1-score values. Furthermore, the confusion matrix and ROC analysis revealed strong discrimination among the disease classes, with only limited errors occurring between visually similar categories. These findings highlight the importance of optimizing the training schedule when adapting pretrained models for plant disease recognition. Overall, the proposed framework provides an effective and scalable approach for chili leaf disease classification while offering an alternative to approaches that primarily rely on architectural modifications.
CME-Insights: A Cognitive Multimodal Explainability Framework for Credit Risk Assessment Using SEC Financial Filings Ankur Agarwal; Shashi Prabha; Raghav Yadav
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7678

Abstract

In financial data analysis, credit risk assessment has traditionally depended on financial ratios. However, a lot of useful information is hidden in company reports, especially in the textual sections. Most of the financial analytics models do not utilize the textual features of financial data. To address this gap, this work proposes the Cognitive Analytics, Multimodal and Explainability (CME-Insights) framework, which is designed to provide clear and data-driven support for financial decision making. The proposed approach combines numerical financial indicators and textual information from the Management Discussion and Analysis (MD&A) sections. These two modalities of data are extracted from SEC 10-K and 10-Q reports. The structured financial modality is drawn from a publicly available corporate credit rating dataset comprising 2,029 records. The model uses 25 financial features along with 11 text-based features. These text features capture characteristics such as sentiment, uncertainty, risk, legal tone, and readability. Loughran-McDonald financial dictionary and the VADER sentiment model are used to extract these features. The best results came from a stacked model that combines CatBoost, LightGBM, and Random Forest base learners with a Logistic Regression meta-classifier. This model achieved an accuracy of 89.36% when ticker symbols were included, and 86.24% without them. SHAP and LIME explainability approaches indicated that the features such as debt ratio and operating cash flow per share play a key role in predicting credit risk. Thus, the CME-Insights framework delivers more accurate and explainable credit risk assessment than traditional financial-ratio-only approaches.
Uncertainty-Guided Noise-Aware Oversampling with Deep CNN for Imbalanced Oil Palm Disease Classification Hartono Hartono; Erianto Ongko; Retna Astuti Kuswardani; Suswati Suswati
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7683

Abstract

Oil palm disease classification is essential for precision agriculture, but its performance is often limited by class imbalance, noisy samples, and overlapping feature distributions. Conventional Convolutional Neural Network (CNN)-based models provide strong feature extraction capabilities, yet they tend to be biased toward majority classes and are sensitive to unreliable training data. Oversampling methods such as the Synthetic Minority Over-sampling Technique (SMOTE) improve class balance, but may amplify noise because synthetic samples are generated without considering sample reliability. This study proposes an uncertainty-guided noise-aware oversampling framework integrated with a deep CNN for imbalanced oil palm disease classification. Aleatoric uncertainty is used to identify and remove noisy samples, while epistemic uncertainty guides synthetic data generation toward informative regions near decision boundaries. A sensitivity analysis identifies the most effective configuration, consisting of 20 forward passes, a dropout rate of 0.5, an aleatoric uncertainty threshold of 0.4, and prediction variance as the epistemic uncertainty measure. Experimental results show that the proposed framework achieves the highest validation accuracy of 92.88% and consistently outperforms CAE, LCNN, CNN, Deep SVM, and SCNN across Accuracy, Precision, Recall, Specificity, F1-Score, Balanced Accuracy, and Cohen’s Kappa. The largest improvements are observed in the minority classes, particularly Ganoderma Initial Infection and Ganoderma Infected. Wilcoxon signed-rank testing confirms that all improvements are statistically significant (p < 0.05). Computational analysis indicates only a moderate and practically insignificant increase in training time, memory usage, and computational complexity. These findings demonstrate that the proposed framework provides an effective and robust solution for imbalanced agricultural image classification.
Benchmarking Transformer Models for Sentiment Analysis on YouTube User Comments Li-Hua Li; Agus Cahyo Nugroho
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7752

Abstract

Social media has become one of the most important platforms for public expression due to its ability to provide users with an unprecedented scale for sharing opinions, sentiments, and experiences. Consequently, social media platforms provide valuable insights into public perception and user sentiment across various topics. This study presents a comparative evaluation of five transformer-based models, namely DistilBERT, BERT, BERTweet, RoBERTa, and Twitter-RoBERTa, on a cleaned and preprocessed YouTube Comments Dataset for sentiment analysis tasks. All models were evaluated under identical experimental settings and preprocessing procedures to reduce textual noise and improve data quality. Each transformer model was fine-tuned under common training conditions to assess its effectiveness in handling informal and user-generated social media content. Experimental results show that Twitter-RoBERTa outperforms other approaches and achieves the best overall accuracy: 90.13% (F1-score: 90.01%), demonstrating its ability to learn from contextual nuances and social media-specific language patterns. In addition, McNemar statistical analysis further supports the statistical significance of many performance differences between the models evaluated including those between Twitter-RoBERTa and smaller general-purpose models such as DistilBERT and BERT. These results demonstrate the value of using domain-specific pretraining on noisy social media text to improve sentiment classification performance and that transformer architectures built with fine-tuning in mind can effectively capture platform specific aspects of linguistics. In summary, this work presents a strong benchmark for transformer-based-sentiment-analysis on YouTube comments and valuable information for future research in social media sentiment analysis.
PATSE: PyTorch-Native Polar Encoding for Runtime Stability in Audio Processing Nuk Ghurroh Setyoningrum; Ema Utami; Kusrini Kusrini; Ferry Wahyu Wibowo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7776

Abstract

Efficient and stable audio feature extraction is essential for real-time AI systems, yet conventional spectral representations often incur preprocessing overhead and framework-conversion dependencies. This study proposes PATSE (Polarized Amplitude Time Spiral Encoding), a PyTorch-native spatial–temporal encoding framework that converts one-dimensional audio into CNN-compatible two-dimensional polar representations while preserving temporal–amplitude information. Evaluated on 100 infant cry samples, PATSE achieved competitive CPU runtime (5.37 ms), improved latency stability over Mel-Spectrogram, and 91% classification accuracy with a Macro-F1 score of 0.85 using a lightweight CNN. These results suggest that PATSE provides an effective balance between computational efficiency, framework integration, and discriminative representation in the evaluated CPU-based infant cry setting, while broader validation is reserved for future work.
An Explainable Multimodal Hybrid Deep Learning Framework for Real-Time IoT-Based Fish Freshness Classification Rian Ordila; Miratu Megasari; Yulanda Yulanda; Yuda Irawan; Refni Wahyuni
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7844

Abstract

Reliable assessment of fish freshness supports product quality, food safety, and consumer acceptance throughout fisheries supply chains. Sensory inspection remains common, but reliance on individual judgment can produce inconsistent assessments and limit monitoring efficiency. Here, a multimodal framework combines Computer Vision, IoT sensing, and Deep Learning to monitor Nile tilapia freshness in realtime. Its visual branch uses YOLO26 to locate fish eyes and EfficientNet B3 with CBAM to classify the extracted regions. A BiLSTM network learns temporal patterns from MQ136 and MQ137 measurements of H₂S and NH₃ associated with spoilage. An MLP then combines the class probabilities from both branches to assign the final freshness category. In the detection experiment, YOLO26 recorded 0.930 precision and 0.953 mAP@0.5. Visual classification with EfficientNet B3 plus CBAM reached 92% accuracy, whereas sensor classification with BiLSTM reached 93%, with AUC values as high as 0.99. Combining the modalities yielded 97% accuracy and a macro average F1 score of 0.97, exceeding the performance of either branch alone. Grad CAM maps located the main visual responses within eye regions relevant to freshness deterioration. These results support the framework's interpretability and its potential use for intelligent fish freshness assessment under near realtime monitoring conditions.
A Hybrid Dynamic Time Warping and Multi-BMU Self-Organizing Map for Time-series Clustering Rina Dewi Indahsari; Siti Sendari; Wahyu Sakti Gunawan Irianto; Samsul Arifin; Dyah Lestari
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7937

Abstract

Time-series clustering remains challenging because many SOM-based studies still improve either temporal similarity measurement or winner adaptation separately, leaving limited evidence on the effect of integrating both components in a single framework. This study proposes a hybrid Self-Organizing Map (SOM) that combines Dynamic Time Warping (DTW) and a multi-Best Matching Unit (multi-BMU) mechanism for temporal pattern clustering. The proposed approach replaces Euclidean distance with DTW in representative-neuron selection and extends learning from a single BMU to a top-k winner scheme with k=3. The model was evaluated on 2,505 room-lighting time-series samples of length 25 collected over 60 weeks in an office building in Indonesia. Four models were compared across 10 independent runs: M1 (standard SOM), M2 (SOM + DTW), M3 (SOM + multi-BMU), and M4 (hybrid SOM + DTW + multi-BMU). The results show that M4 achieved the best clustering quality, with the highest mean Silhouette score (0.768300), the lowest Davies–Bouldin Index (0.4011), and the highest Calinski–Harabasz Index (233.1750). In contrast, M1 retained the lowest mean Topographic Error (0.150858). Statistical tests confirmed significant differences among models. Although the proposed model increases computational complexity compared with standard SOM, the use of a DTW window constraint helps reduce the alignment cost while preserving temporal sensitivity. The integration of DTW and multi-BMU substantially improves temporal cluster quality, although it is accompanied by reduced topological preservation and increased computational complexity.
Reliable Indonesian Academic Service Chatbot Using Retrieval-Augmented Generation and Adaptive Refusal Jarot Budiasto; Tatik Melinda Tallulembang; Selfina Pare; Muhammad Hasbi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.8018

Abstract

Academic service information is often stored in lengthy, formal, and distributed university documents, making accurate access difficult. Generative chatbots can improve access but may answer unsupported questions unless retrieval and refusal are controlled. This study proposes a reliability-oriented Retrieval-Augmented Generation (RAG) chatbot for Indonesian academic services integrating BGE-M3, FAISS, adaptive refusal thresholding, rule-based guardrails, Qwen2.5, and retry-on-refusal. A controlled experiment used 12 official documents and 160 Indonesian questions across eight categories. The final configuration achieved Precision@5 of 0.7250, Recall@5 of 0.9125, MRR of 0.8940, nDCG@5 of 0.8888, and mean semantic similarity of 0.8516. All 16 expected-refusal questions were refused and none of the 144 answerable questions was falsely refused, yielding observed refusal accuracy of 1.0000 and a false refusal rate of 0.0000. Retry-on-refusal reduced the false refusal rate from 0.0556 to 0.0000 and increased answerable-only similarity from 0.8150 to 0.8392. These results provide initial evidence that combining retrieval confidence, guardrails, and retry supports more reliable behavior within the controlled benchmark. Because the refusal subset was small and institution-specific, larger evaluations using naturally occurring student queries are required before inferring operational reliability.
Heterogeneous Stacking Ensemble with SMOTE-Based Oversampling for Agricultural Commodity Price Prediction under Extreme Class Imbalance Yessica Siagian; Neni Mulyani; Jeperson Hutahaean; Dinda Maharani; Jenny Erlita
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.8065

Abstract

Predicting agricultural commodity prices is vital for food security and market stability, but price data is highly non-linear, high-cardinality, and severely imbalanced, rendering conventional accuracy metrics misleading. This study proposes a heterogeneous stacking ensemble of LightGBM, XGBoost, and Random Forest base learners with a LightGBM meta-learner, evaluated against five BorderlineSMOTE oversampling variants and four ensemble configurations under a 282:1 class imbalance. A controlled ablation across six configurations — including a new factorial design that isolates the contributions of oversampling and an MLP base learner — demonstrates that performance is driven by the stacking architecture rather than by synthetic oversampling or deep learning components. The ensemble without oversampling achieves MCC = 0.9509 and AUC-OvR = 0.9908 on the held-out test set, while the addition of an MLP base learner yields no consistent improvement (|ΔMCC| < 0.008 across both SMOTE and no-SMOTE conditions). These findings identify cost-sensitive heterogeneous stacking as an effective and computationally tractable strategy for highly imbalanced tabular agricultural data, and establish that synthetic oversampling and MLP-based components are unnecessary under these conditions.

Page 118 of 119 | Total Record : 1185

 115   116   117   118   119 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol 10 No 5 (2026): October 2026 (In progress) Vol 10 No 4 (2026): August 2026 Vol 10 No 3 (2026): June 2026 Vol 10 No 2 (2026): April 2026 Vol 10 No 1 (2026): February 2026 Vol 9 No 6 (2025): December 2025 Vol 9 No 5 (2025): October 2025 Vol 9 No 4 (2025): August 2025 Vol 9 No 3 (2025): June 2025 Vol 9 No 2 (2025): April 2025 Vol 9 No 1 (2025): February 2025 Vol 8 No 6 (2024): December 2024 Vol 8 No 5 (2024): October 2024 Vol 8 No 4 (2024): August 2024 Vol 8 No 3 (2024): June 2024 Vol 8 No 2 (2024): April 2024 Vol 8 No 1 (2024): February 2024 Vol 7 No 6 (2023): December 2023 Vol 7 No 5 (2023): October 2023 Vol 7 No 4 (2023): August 2023 Vol 7 No 3 (2023): Juni 2023 Vol 7 No 2 (2023): April 2023 Vol 7 No 1 (2023): February 2023 Vol 6 No 6 (2022): Desember 2022 Vol 6 No 5 (2022): Oktober 2022 Vol 6 No 4 (2022): Agustus 2022 Vol 6 No 3 (2022): Juni 2022 Vol 6 No 2 (2022): April 2022 Vol 6 No 1 (2022): Februari 2022 Vol 5 No 6 (2021): Desember 2021 Vol 5 No 5 (2021): Oktober2021 Vol 5 No 4 (2021): Agustus 2021 Vol 5 No 3 (2021): Juni 2021 Vol 5 No 2 (2021): April 2021 Vol 5 No 1 (2021): Februari 2021 Vol 4 No 6 (2020): Desember 2020 Vol 4 No 5 (2020): Oktober 2020 Vol 4 No 4 (2020): Agustus 2020 Vol 4 No 3 (2020): Juni 2020 Vol 4 No 2 (2020): April 2020 Vol 4 No 1 (2020): Februari 2020 Vol 3 No 3 (2019): Desember 2019 Vol 3 No 2 (2019): Agustus 2019 Vol 3 No 1 (2019): April 2019 Vol 2 No 3 (2018): Desember 2018 Vol 2 No 2 (2018): Agustus 2018 Vol 2 No 1 (2018): April 2018 Vol 1 No 3 (2017): Desember 2017 Vol 1 No 2 (2017): Agustus 2017 Vol 1 No 1 (2017): April 2017 More Issue