Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal International Journal of Informatics and Computation
Bulkis Kanata
Universitas Mataram, Indonesia
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparing Cat Disease Classification using CNN Architectures Ria Wahyusari; Bulkis Kanata; Sudi M Al Sasongko
International Journal of Informatics and Computation Vol. 8 No. 2 (2026): International Journal of Informatics and Computation
Publisher : University of Respati Yogyakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/ijicom.v8i2.298

Abstract

Accurate classification of feline skin diseases can support early identification and improve access to preliminary veterinary information. This study evaluates three pretrained convolutional neural network (CNN) architectures, ConvNeXtV2 (Atto), MobileNetV4 (ConvSmall), and RegNet (Y-008), for classifying five categories of cat images: feline acne, flea allergy, scabies, healthy cats, and ear mites. We utilize a balanced dataset of 3,000 images, with 600 images per class, and apply image preprocessing and online data augmentation to improve model training. We evaluate the models using three-fold cross-validation and a separate test set of 300 images. The results show that ConvNeXtV2 achieves the highest mean cross-validation accuracy of 96.48%, followed by RegNet at 96.33% and MobileNetV4 at 92.30%. However, RegNet achieves the best test performance, with 89.67% accuracy, 92.61% macro precision, 89.67% macro recall, and an 89.81% macro F1-score. RegNet also achieves 70.00% recall for scabies, outperforming ConvNeXtV2 and MobileNetV4. All three models achieve 100% recall for healthy cats, while scabies remains the most challenging class due to frequent misclassification as feline acne and ear mites. The application rejects predictions with confidence below 50% and clarifies that its output does not replace a veterinary diagnosis. These findings demonstrate the potential of pretrained CNN architectures for feline skin disease classification and identify RegNet as the most effective model among the evaluated architectures.
Improving Performance of LoRa in Agricultural Land Temperature and Humidity Monitoring System Ardhika Rizky Ramadhan; Bulkis Kanata; A Sjamsjiar Rachman
International Journal of Informatics and Computation Vol. 8 No. 2 (2026): International Journal of Informatics and Computation
Publisher : University of Respati Yogyakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/ijicom.v8i2.302

Abstract

Limited cellular communication infrastructure, complex topography, and dense vegetation in rural areas pose major challenges to the implementation of smart agriculture. This study aims to analyze the performance and stability of a 433 MHz LoRa wireless communication network under Non-Line-of-Sight (NLOS) conditions and evaluate the accuracy of temperature and soil moisture sensors in an automatic irrigation prototype. We conducted field tests in Bentenu Hamlet, Banyu Urip Village, West Lombok Regency, at distances of 100 m, 300 m, and 500 m under two propagation scenarios: dense-vegetation NLOS and hilly-terrain NLOS. The results showed that the dense-vegetation path at 100 m achieved excellent signal quality, with an average Received Signal Strength Indicator (RSSI) of −39.67 dBm and a Signal-to-Noise Ratio (SNR) of +12.75 dB. At the maximum distance of 500 m, signal quality degraded to −101.50 dBm RSSI and −0.62 dB SNR under dense-vegetation conditions, classified as fair, and to −105.30 dBm RSSI and −8.63 dB SNR under hilly-terrain conditions, classified as poor. Despite the declining signal quality and negative SNR, the recorded packet loss remained at 0.00% across all tested distances and propagation conditions. Regarding sensor accuracy, the capacitive soil moisture sensor V1.2 achieved a Mean Absolute Error (MAE) of 1.24% volumetric water content (VWC), corresponding to a reported accuracy of 98.76%. The DHT11 air temperature sensor achieved an MAE of 0.38 °C, with a reported accuracy of 99.62%, compared with the standard reference instrument. These findings demonstrate the potential of 433 MHz LoRa technology for supporting automatic irrigation in rural agricultural areas with challenging terrain.
Co-Authors A Sjamsjiar Rachman Ardhika Rizky Ramadhan Ria Wahyusari Sudi M Al Sasongko