cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mochammad Anshori
Contact Email
moanshori@itsk-soepraoen.ac.id
Phone
+626285733333284
Journal Mail Official
jesica@itsk-soepraoen.ac.id
Editorial Address
Jl. S. Supriadi No.22, Sukun, Malang, Jawa Timur, Indonesia (Kampus 2 ITSK Soepraoen)
Location
Kota malang,
Jawa timur
INDONESIA
The Journal of Enhanced Studies in Informatics and Computer Applications
Published by Institut Teknologi, Sains, dan Kesehatan RS.DR. Soepraoen Kesdam V/BRW
ISSN : 30466997     EISSN : 30466938     DOI : https://doi.org/10.47794/jesica.v1i1
Core Subject : Science,
Computer Science & IT
Journal of Enhanced Studies in Informatics and Computer Applications (JESICA) is an international peer-reviewed journal that aims to provide the best analysis and discussion to its readers in the development scope of Data Science, Software Engineering, Computer Applications, Health Informatics, and Internet of Things. JESICA publishes original research findings and quality scientific articles that present cutting-edge approaches including methods, techniques, tools, implementation, and applications.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 25 Documents
 1   2   3 
Performance-Storage Trade-Off Analysis of MongoDB Indexing Strategies Using Large-Scale E-Commerce Data Kunti Inayati; Umi Chotijah
Journal of Enhanced Studies in Informatics and Computer Applications Vol. 3 No. 2 (2026): JESICA Vol. 3 No. 2 2026
Publisher : Institut Teknologi, Sains, dan Kesehatan RS.DR. Soepraoen Kesdam V/BRW

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47794/jesica.v3i2.45

Abstract

Indexing strategy in document-oriented databases represents a fundamental design decision that directly shapes both query performance and storage consumption, yet empirical evidence quantifying this trade-off at production-grade scale remains limited in existing literature. This study evaluated three indexing configurations in MongoDB, namely no index, single-field index on product identifier, and compound index on product identifier together with order status, across four collection sizes of 1 million, 5 million, 10 million, and 13 million documents derived from a synthetic large-scale e-commerce dataset obtained from Kaggle containing approximately 13 million order-line records. A controlled benchmarking procedure was employed in which each indexing condition was tested under identical query workloads repeated 30 times per configuration, with query execution time, index creation time, and index storage size recorded as evaluation metrics. Results showed that unindexed collections produced full collection scans with mean execution times scaling from 1,247.70 ms at 1 million documents to 33,300.07 ms at 13 million documents, while both indexed conditions reduced execution times to single-digit milliseconds by activating index scan paths. For multi-predicate queries, the compound index outperformed the single-field index by a factor of 6.8 at full scale, recording 1.33 ms against 9.03 ms, while incurring only 1 MB of additional storage overhead. These findings indicate that compound indexing represents the most balanced strategy for high-volume e-commerce query workloads, delivering substantial performance gains at negligible additional storage cost.
Comparative Analysis of Texture Feature Extraction-Based Machine Learning Algorithms for Road Surface Condition Classification Naufal Alif Vivaldi; Novelia Puspita; Hilda Hilda Mujaddidah; Riski Lestari; Risqy Siwi Pradini
Journal of Enhanced Studies in Informatics and Computer Applications Vol. 3 No. 2 (2026): JESICA Vol. 3 No. 2 2026
Publisher : Institut Teknologi, Sains, dan Kesehatan RS.DR. Soepraoen Kesdam V/BRW

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47794/jesica.v3i2.46

Abstract

Road surface conditions play a crucial role in ensuring transportation comfort and safety. Conventional road inspection methods that rely on manual observation are often time-consuming, expensive, and prone to subjectivity. This study proposes an automated approach to classify road surface conditions using texture-based feature extraction and machine learning algorithms. A total of 802 road images were independently collected, representing three classes: good, fair, and damaged. The images were preprocessed through resizing, grayscale conversion, Contrast Limited Adaptive Histogram Equalization (CLAHE), and pixel normalization to improve image quality. Texture features were then extracted using Gray Level Co-occurrence Matrix (GLCM), including contrast, homogeneity, energy, and correlation. The extracted features were used as input to four classification algorithms: Support Vector Machine (SVM), k-Nearest Neighbor (KNN), Random Forest, and Naive Bayes. Experimental results show that KNN achieved the best performance with 96.27% accuracy, followed by SVM and Random Forest with comparable results. Naive Bayes performed the lowest due to its detrimental assumption of feature independence. These findings demonstrate that texture-based features combined with appropriate machine learning algorithms can effectively classify road surface conditions. This approach has strong potential for implementation in automated, real-time road monitoring systems, especially on devices with limited computing resources, contributing to more efficient and objective infrastructure management.
Aspect-Based Sentiment Analysis of Indonesian Healthcare Application Reviews Using Latent Dirichlet Allocation and IndoBERT Carli Apriansyah Hutagalung; Muhammad Arib Alwansyah; Tiara Husnul Khotimah
Journal of Enhanced Studies in Informatics and Computer Applications Vol. 3 No. 2 (2026): JESICA Vol. 3 No. 2 2026
Publisher : Institut Teknologi, Sains, dan Kesehatan RS.DR. Soepraoen Kesdam V/BRW

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47794/jesica.v3i2.47

Abstract

The increasing use of digital healthcare applications has generated large volumes of user reviews that reflect user experiences and satisfaction. This study aimed to perform Aspect-Based Sentiment Analysis (ABSA) of Indonesian healthcare application reviews using Latent Dirichlet Allocation (LDA) and IndoBERT. A total of 3,000 reviews were collected from Halodoc, Alodokter, and SATUSEHAT Mobile through the Google Play Store. After preprocessing, 1,460 valid reviews were analyzed. LDA was applied to identify discussion aspects, while IndoBERT was used to classify review sentiments into positive, neutral, and negative categories. The analysis identified seven major aspects related to consultation services, doctor responsiveness, medication delivery, payment processes, and system accessibility. Negative sentiment dominated the dataset (51.78%), followed by positive (40.82%) and neutral (7.40%) sentiments. Doctor Responsiveness and Service Quality achieved the highest positive sentiment (86.57%), whereas Login, OTP, and System Access Problems showed the highest negative sentiment (89.71%). The findings indicated that users appreciated healthcare professionals but frequently reported technical and operational issues. The study concluded that improvements in system reliability, authentication mechanisms, payment services, and medication delivery processes are essential to enhance user satisfaction with Indonesian healthcare applications
A Systematic Review of Machine Learning Approaches for K-Pop Concert Sentiment Analysis on X Yunia Putri Adifa; Carli Apriansyah Hutagalung
Journal of Enhanced Studies in Informatics and Computer Applications Vol. 3 No. 2 (2026): JESICA Vol. 3 No. 2 2026
Publisher : Institut Teknologi, Sains, dan Kesehatan RS.DR. Soepraoen Kesdam V/BRW

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47794/jesica.v3i2.48

Abstract

K-pop concerts in Indonesia generate intensive digital discussion on X/Twitter, yet studies that directly combine concert-related objects, X data, and machine-learning-based sentiment classification remain limited. This study conducts a systematic literature review to map research objects, methods, preprocessing techniques, evaluation results, and research gaps in K-pop sentiment analysis. The selection process followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework. A total of 5,674 records were collected, 4,618 duplicates were removed, 1,056 records were screened, and 20 articles were included in the final synthesis. The findings show that X is the dominant platform. Previous studies more frequently examine K-pop groups, fandom, the Korean Wave, and cyberbullying rather than direct concert experiences. Naive Bayes remains widely used because it is simple, efficient, and suitable for high-dimensional text data, although Support Vector Machine and transformer-based models often provide stronger performance in specific settings. Classification quality is strongly affected by non-standard language normalization, multilingual content, class balance, feature weighting, and labeling consistency. The main gap is the absence of an Indonesian K-pop concert sentiment-analysis design that combines domain-aware preprocessing, per-class evaluation, and aspect-level interpretation of ticketing, promoters, venues, safety, and audience experience.
Penta‑Class Classification of Hepatitis Virus DNA Sequences Using a 1D‑CNN for Enhanced Differential Diagnosis Mochammad Anshori; Mentari Putri Jati
Journal of Enhanced Studies in Informatics and Computer Applications Vol. 3 No. 2 (2026): JESICA Vol. 3 No. 2 2026
Publisher : Institut Teknologi, Sains, dan Kesehatan RS.DR. Soepraoen Kesdam V/BRW

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47794/jesica.v3i2.51

Abstract

Despite advances in molecular testing, the genetic similarity among hepatitis strains and the complexity of their clinical presentations often confound traditional diagnostic approaches, underscoring the urgent need for automated, sequence‑intelligent solutions. This study developed a pure one‑dimensional Convolutional Neural Network (1D‑CNN) to classify five hepatitis virus types (HAV, HBV, HCV, HDV, HEV) directly from raw DNA sequences, eliminating complex preprocessing such as k‑mer segmentation or external optimization. A total of 500 complete genomic sequences (100 per class) were retrieved from the NCBI Virus database. Following one‑hot encoding and sequence padding, the proposed 1D‑CNN architecture—employing convolutional feature extraction with batch normalization and regularization—was trained using the Adam optimizer and categorical cross‑entropy loss. Performance was evaluated using accuracy, precision, recall, F1‑score, Matthews Correlation Coefficient (MCC), ROC‑AUC, and precision‑recall curves. The model achieved an overall accuracy of 95%, MCC of 0.9395, macro precision of 0.9571, and macro recall of 0.9500. ROC‑AUC values reached 1.00 for four classes and 0.97 for HDV, while precision‑recall average precision ranged from 0.971 to 1.00. The confusion matrix revealed minimal misclassifications, primarily between HEV and HDV, confirming that the model autonomously extracts discriminative nucleotide patterns for reliable multi‑species classification. This study contributes an alignment‑free, computationally efficient, and reproducible approach for hepatitis virus typing, outperforming many previous methods reliant on manual feature engineering or heuristic optimization. Future work should validate the model on clinical samples and explore the interpretability of learned motifs.

Page 3 of 3 | Total Record : 25

 1   2   3 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 2 (2026): JESICA Vol. 3 No. 2 2026 Vol. 3 No. 1 (2026): JESICA Vol. 3 No. 1 2026 Vol. 2 No. 1 (2025): JESICA Vol. 2 No. 1 2025 Vol. 1 No. 2 (2024): JESICA Vol. 1 No. 2 2024 Vol. 1 No. 1 (2024): JESICA Vol. 1 No. 1 2024