Claim Missing Document
Check
Articles

Found 15 Documents
Search

Pemanfaatan Quick Response Code Sebagai Media Informasi Destinasi Wisata Pintar di Provinsi Bali Sugianta, I Kadek Arya; Patrianingsih, Ni Kadek Winda
CESS (Journal of Computer Engineering, System and Science) Vol. 9 No. 1 (2024): January 2024
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/cess.v9i1.53158

Abstract

Sektor pariwisata merupakan industri utama Bali, barometer pembangunan pariwisata nasional. Kehadiran pandemi Covid 19 membawa perubahan dengan tantangan yang sebelumnya tidak terpikirkan. Industri pariwisata Bali merosot tajam hingga negatif sejak 2020, dengan berbagai sektor lumpuh, terutama di sektor ekonomi, di sektor pariwisata dan ketenagakerjaan, dengan pemutusan hubungan kerja (PHK) dan perusahaan pariwisata. Era new normal turut memaksa manusia untuk memanfaatkan teknologi digital semaksimal mungkin pada setiap sektor kehidupan, termasuk pada bidang pariwisata. Salah satu teknologi digital itu adalah penggunaan Quick Respon Code (QR-Code). Penelitian yang dilakukan bertujuan untuk membangun sistem informasi destinasi wisata pintar yang responsif dan berbasis web yang diintegrasikan dengan teknologi Quick Response Code. Metode dalam penelitian ini menggunakan penelitian deskriptif dengan menggunakan pendekatan kualitatif. Selain itu, penelitian ini menggunakan pendekatan penelitian dan pengembangan (R&D). Penelitian ini telah mencapai tahap keenam pengembangan sistem, yaitu pembuatan prototipe produk akhir. Hasil penelitian data lapangan yang dilakukan untuk mengevaluasi pemanfaatan QR-Code menunjukkan bahwa teknologi ini berguna dan dapat digunakan dengan baik untuk membangun Destinasi Wisata Pintar di Bali. Berdasarkan analisis yang telah dilakukan, penggunaan QR-Code prototipe pada objek wisata menunjukkan bahwa itu adalah pilihan yang tepat untuk diterapkan pada berbagai objek wisata.
Dampak Filter Digital Terhadap Kinerja Convolutional Neural Network pada Klasifikasi Suara Lingkungan Sugianta, I Kadek Arya
Jurnal Teknik Informatika dan Sistem Informasi Vol 12 No 1 (2026): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v12i1.14018

Abstract

Often, telephony-style bandwidth restriction techniques are applied raw to environmental sound classification systems without sufficient validation. To test their effectiveness, this study evaluates the impact of various digital filters (Low-Pass, High-Pass, Band-Pass, Band-Stop) on CNN performance on the ESC-50 dataset. After establishing the Log-Mel Spectrogram as the best input feature (surpassing MFCC), experiments proved that standard Band-Pass filters (300-3400 Hz) and Low-Pass filters actually reduced accuracy. This confirms that environmental sounds require a broad frequency spectrum (broadband), especially at high frequencies. Positive findings were obtained from the use of a low-order High-Pass Filter (HPF) (FIR-32) with a cut-off of 1000 Hz, which successfully increased accuracy to 66.20% above the baseline. Spectral analysis shows that this configuration successfully removes low noise without triggering transient smearing (time distortion). Therefore, this study recommends low-order HPF as the new standard, while suggesting the use of adaptive filters (learnable filters) in the future.
- IN SILICO STUDY OF DERIVATIVE COMPOUNDS OF GALANGAL PLANTS AS ANTI-INFLAMMATORY I Wayan Tanjung Aryasa; I Kadek Arya Sugianta
Jurnal Penelitian Pendidikan IPA Vol 9 No 8 (2023): August
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v9i8.3042

Abstract

A Inflammation is the basis of pathogenesis of several diseases, both degenerative and non-degenerative diseases. Galangal plants which are commonly found in Indonesia are commonly used as traditional medicines for several diseases and also have secondary metabolite compounds that are useful as anti-inflammatory. In this study, an in silico approach in the form of molecular docking has been applied to 5 compounds derived from the galangal plant to important inflammatory molecular targets such as the cyclooxygenase-2 (COX-2) receptor. Analysis of the biological activity of compounds derived from the galangal plant using the WAY2DRUG PASS prediction server. Prediction results of physicochemical properties of compounds derived from galangal plant using the SWISS-ADME server. This study aims to predict the ability of 5 compounds derived from the galangal plant to inhibit the COX-2 enzyme. Detailed information has been obtained using a molecular docking approach. Docking simulations for 5 compounds derived from the galangal plant have been carried out through the Autodock 4.2 application which is embedded in the MGL Tools 1.5.6 application. The molecular interactions of compounds derived from galangal against COX-2 receptors were visualized using Discovery Studio (Biova) software. Based on the results of the research that has been carried out, it can be concluded that the test compound Galanganal has the best affinity when compared to the compounds Galanganol A, Galanganol B, Galanganol C and Galangin. This can be seen from the bond free energy value of -8.98 kcal/mol and the inhibition constant of 261.59 nM. These results indicate that the Galanganal test compound has potential as an anti-inflammatory agent. However, further research is needed to study more compounds derived from the galangal plant to isolate the best conformation.
Analisis Ketahanan Lightweight Audio Spectrogram Transformer pada Identifikasi Pembicara Kondisi Berderau I Kadek Arya Sugianta; Gde Palguna Reganata
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 11 No. 2 (2026): May 2026
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.6170

Abstract

The use of deep learning models for speaker identification on devices with limited computational resources requires significant architectural optimization. This study evaluates the performance and robustness of the Lightweight Audio Spectrogram Transformer (AST) architecture, which has been extremely compressed to 570,536 parameters. The proposed method uses low-resolution Mel-Spectrogram representations (64x64 pixels) as input for a global self-attention mechanism. Testing was conducted using a 5-Fold Cross Validation scheme on a dataset injected with non-stationary environmental noise from the ESC-50 corpus at various Signal-to-Noise Ratio (SNR) levels. Experimental results show that under ideal conditions, the model achieves a solid average validation accuracy of 70.86% ± 2.69% with a Macro Average F1-score of 0.68 ± 0.03. However, the model’s performance degrades sharply to 17.61% at an SNR of 5 dB and drops to 9.21% under extreme conditions at an SNR of 0 dB. These findings reveal a critical trade-off where radical parameter compression leads to the loss of spectral feature redundancy that acts as an implicit noise filter. This study concludes that while lightweight Transformer mechanisms are highly efficient for Edge AI, the integration of pre-processing modules or noise-robust training strategies is an absolute necessity to maintain identification integrity in noisy real-world environments.
Comparing Audio and Visual Transfer Learning for Environmental Sound Classification Sugianta, I Kadek Arya
Journal of Information Technology and Computer Science Vol. 11 No. 1: April 2026
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.111841

Abstract

Environmental Sound Classification (ESC) faces significant challenges related to data scarcity and unstructured acoustic signal variability. This study evaluates the effectiveness of a Visual Transfer Learning approach by transforming audio signals into Mel-Spectrogram representations for classification using Computer Vision architectures. A comparative study was conducted on the ESC-50 dataset, benchmarking visual-based models (EfficientNet-B0, ResNet-50) against specialized audio models (Pre-trained Audio Neural Networks/PANNs). Experimental results demonstrate that EfficientNet-B0, optimized with MixUp augmentation, achieved the highest performance with 83.33% accuracy and 83.50% F1-Score, outperforming ResNet-50 (80.00%) and significantly surpassing the PANNs (Cnn14) model, which only reached 66.33%. The underperformance of PANNs indicates issues with over-parameterization on small-scale datasets. Further validation using Gradient-weighted Class Activation Mapping (Grad-CAM) confirmed that the EfficientNet-B0 model precisely learned semantic features by distinguishing active sound patterns from silence and background noise. These findings confirm that lightweight visual architectures possess superior transferability and generalization compared to massive audio models in data-constrained scenarios.