Garuda - Garba Rujukan Digital

Dynamics of CO2 Emission Flux from the Vegetation Canopy Percentage in the Suropati City Park Ecosystem Elvira, Ade Irma; Ramadhani, Muhammad Reza; Patria, Mufti Petala; Nurdin, Erwin; Vasenev, Ivan Ivanovich
ADALAH Vol 9, No 6 (2025)
Publisher : UIN Syarif Hidayatullah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/adalah.v9i6.44821

In recent years, fossil fuel usage and industrial activities have significantly increased, leading to higher greenhouse gas emissions and impacting global temperature, contributing to global warming and climate change. The carbon footprint measures these emissions through carbon flux rates, influenced by climate conditions, soil and water uptake, organic matter, and microbial activities. The experiment used a gas analyzer and gas chromatograph to measure samples under three conditions. The highest average flux rate was in fully enclosed vegetation (4.04 g CO2/m²/day), followed by not enclosed vegetation (4.01 g CO2/m²/day), and the lowest was 3.91 g CO2/m²/day. Results indicate that vegetation and urban parks reduce CO2 emission fluxes, with each area's vegetation state affecting soil and air temperature, pH content, and soil moisture. However, many aspects such as soil type and climate cognition can influence fluctuation of carbon fluxes in each condition.

Retinal Blood Vessel Segmentation Based on Encoder and Decoder Networks Using Weighted Cross Entropy Loss Function Qomariah, Dinial Utami Nurul; Tjandrasa, Handayani; Elvira, Ade Irma
ADALAH Vol 9, No 6 (2025)
Publisher : UIN Syarif Hidayatullah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/adalah.v9i6.44857

Retinal disease that has a major impact on human vision is diabetic retinopathy. Diabetic retinopathy is a disease caused by advanced diabetic mellitus. Early detection of the disease is very importance. An automated system that can recognize retinal blood vessel abnormalities is very useful for providing quick information to prevent further damage to the retina. In this study, we propose an automated system for segmenting the blood vessels in retinal fundus images using semantic segmentation based on pre-trained from VGG transfer learning and using median frequency balancing weights for the cross entropy loss function. The median frequency weights are to balance the importance of blood vessel and background pixels to get more accurate training results. The integration of encoder and decoder networks utilizing VGG transfer learning and semantic segmentation can segment retinal blood vessels with a sensitivity value of 85.48% using the DRIVE and STARE database.

Automatic Pill Detection Using Faster R-CNN with an AlexNet Backbone Elvira, Ade Irma; Kurniasar, Arvita Agus; Maulana, Bima Wahyu; Nurul Qomariah, Dinial Utami
Jurnal Multidisiplin West Science Vol 4 No 12 (2025): Jurnal Multidisiplin West Science
Publisher : Westscience Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/jmws.v4i12.3068

Object detection is a crucial component in the development of automated systems in the healthcare domain, particularly in pharmaceutical applications such as pill identification and management. One of the main challenges in image-based pill detection systems is achieving high accuracy and robust generalization under variations in pill shape, color, and illumination conditions. This study applies the Faster R-CNN framework with an AlexNet backbone to detect and classify pill objects in digital images. The model is trained using multiple epoch configurations to analyze the effect of training duration on detection performance. Experimental results show that the proposed approach achieves an accuracy of up to 98%, demonstrating strong detection capability. Increasing the number of training epochs improves the stability and consistency of pill recognition. These results indicate that AlexNet-based Faster R-CNN is effective for pharmaceutical applications, particularly in drug distribution, packaging, and pill counting systems that require high precision and reliability.

Soil CO₂ Emissions in Jakarta Urban Forests: The Role of Canopy Cover Versus Environmental Factors Elvira, Ade Irma; Arif, Ibrahim; Nainggolan, Carla Mariana; Renita, Destia Puri Prela; Putri, Nadia Asmawari; Patria, Mufti Petala; Nurdin, Nurdin; Vasenev, Ivan Ivanovich
Jurnal Manajemen Hutan Tropika Vol. 32 No. 1 (2026)
Publisher : Institut Pertanian Bogor (IPB University)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.7226/jtfm.32.1.27

Increasing carbon dioxide (CO2) emissions encourages global warming and climate change. Soil can store CO2 emissions, which are absorbed by vegetation. Studies on the dynamics of soil CO2 gas emission fluxes with differences in the percentage of vegetation canopy cover in the urban forest ecosystem of the Jakarta Region have never been frequently carried out. This research aims to analyze and compare the dynamics of soil CO2 gas emission fluxes in the urban forest ecosystem of the Jakarta Region with different percentages of vegetation canopy cover and analyze the relationship between air temperature, soil moisture, soil temperature, and soil acidity (pH) with carbon gas emission fluxes soil dioxide. The research method used is the greenhouse gas capture method, which uses a chamber to measure environmental factors and data analysis using the Kruskal-Wallis test and Spearman correlation. The results showed no significant difference between the percentage of vegetation canopy cover in the urban forest ecosystem and the soil CO2 gas emissions flux. Environmental factors related to the flux of CO2 emissions from soil in the urban forest ecosystem of the Jakarta Region are soil moisture and soil pH. Further research is recommended to measure other environmental factors, such as nutrients and soil organic carbon, to obtain more comprehensive research results on the dynamics of soil CO2 gas emission fluxes.

PENERAPAN SISTEM MONITORING PERTUMBUHAN JAGUNG BERBASIS IOT DAN MACHINE LEARNING UNTUK MENDUKUNG PERTANIAN CERDAS Dinial Utami Nurul Qomariah; Ade Irma Elvira; Ratna Yuniati
JMM (Jurnal Masyarakat Mandiri) Vol 10, No 3 (2026): Juni
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jmm.v10i3.39143

Abstrak: Kegiatan pengabdian kepada masyarakat ini dilaksanakan pada kelompok tani di Desa Jembatan, Kecamatan Kesamben, Kabupaten Jombang, yang didominasi oleh komoditas padi dan jagung. Permasalahan utama mitra meliputi keterbatasan pemantauan kondisi lahan secara real-time serta pengelolaan irigasi yang masih konvensional. Kegiatan ini bertujuan meningkatkan pemahaman dan kapasitas petani dalam pemanfaatan teknologi pertanian cerdas melalui implementasi sistem monitoring pertumbuhan jagung berbasis Internet of Things (IoT) dan Machine Learning. Pelaksanaan kegiatan menggunakan pendekatan kolaborasi multipihak antara kelompok tani, akademisi, dan media dengan metode Participatory Rural Appraisal (PRA). Evaluasi dilakukan melalui pretest–posttest untuk mengukur peningkatan hard skill dan soft skill. Hasil evaluasi menunjukkan adanya peningkatan rata-rata nilai dari 50,25 menjadi 78,75 atau sebesar 58,8%. Kegiatan ini berkontribusi dalam mendorong penerapan pertanian cerdas secara berkelanjutan.Abstract: This community service activity was conducted with a farmer group in Desa Jembatan, Kecamatan Kesamben, Kabupaten Jombang, where agricultural activities are predominantly focused on rice and corn. The main problems faced by the partners include limitations in real-time land condition monitoring and conventional irrigation management practices. This activity aims to enhance farmers’ understanding and capacity in utilizing smart agriculture technologies through the implementation of a corn growth monitoring system based on the Internet of Things (IoT) and Machine Learning. The implementation employed a multi-stakeholder collaboration approach involving farmer groups, academics, and media using the Participatory Rural Appraisal (PRA) method. Evaluation was carried out using a pretest–posttest approach to measure improvements in both hard skills and soft skills. The evaluation results indicate an increase in the average score from 50.25 to 78.75, representing an improvement of 58.8%. This activity contributes to promoting the sustainable adoption of smart agriculture.

Automatic Pill Counting Using YOLOv8 to Improve Medication Distribution Accuracy Dinial Utami Nurul Qomariah; Ade Irma Elvira; Arvita Agus Kurniasari; Bima Wahyu Maulana
International Journal of Public Health Excellence (IJPHE) Vol. 5 No. 2 (2026): January-May
Publisher : PT Inovasi Pratama Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55299/ijphe.v5i2.1724

Object detection is a critical component in various modern applications, including healthcare systems, smart agriculture, and industrial automation. The main challenge in developing detection systems lies in achieving high accuracy and strong generalization capabilities under diverse image conditions. This study aims to implement and evaluate the YOLOv8 model, a detection method known for its speed and efficiency. The model is trained using two scenarios—10 epochs and 50 epochs—to examine the impact of training duration on system performance. Evaluation results show that training for 10 epochs produces very good performance, with a precision of 0.98, recall of 0.94, and mAP of 0.98. Increasing the training to 50 epochs yields even more optimal results, achieving a precision of 0.99, recall of 1.00, and mAP of 0.99. Based on these findings, YOLOv8 demonstrates excellent adaptability to the dataset and is suitable for real-time detection applications that require high accuracy

Grade and Disease Detection of Dragon Fruit based on Modified VGGNet with Identity Mapping Dinial Utami Nurul Qomariah; Ade Irma Elvira; Syifa Nurhayati
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i2.1516

In the agricultural sector, dragon fruit is one of the most frequently harvested fruits throughout the year, regardless of the season. To ensure optimal quality during the harvest period, fruit monitoring should begin from the immature stage. However, dragon fruit is highly susceptible to various diseases, particularly as it approaches ripeness. Therefore, there is a growing need for an automated system that can classify the quality grade of dragon fruit. In addition, such a system should also be able to detect potential diseases affecting fruit. In this study, we propose a modified VGGNet architecture integrated with Identity Mapping. The original VGGNet serves as the backbone. Identity Mapping is then incorporated into each block to improve training efficiency and computational performance. At the final stage, the fully connected and classification layers are fine-tuned to enhance overall accuracy. The proposed method is evaluated using a dragon fruit dataset collected from Bondowoso. Experimental results demonstrate that the proposed approach achieves superior performance, with 99.9% accuracy, recall, and precision. It also outperforms baseline models, including VGG16, AlexNet, and EfficientNet variants B0–B3 and B5–B6.

Dynamics of CO2 Emission Flux from the Vegetation Canopy Percentage in the Suropati City Park Ecosystem Ade Irma Elvira; Muhammad Reza Ramadhani; Mufti Petala Patria; Erwin Nurdin; Ivan Ivanovich Vasenev
BULETIN ADALAH Vol. 9 No. 6 (2025)
Publisher : UIN Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/adalah.v9i6.44821

In recent years, fossil fuel usage and industrial activities have significantly increased, leading to higher greenhouse gas emissions and impacting global temperature, contributing to global warming and climate change. The carbon footprint measures these emissions through carbon flux rates, influenced by climate conditions, soil and water uptake, organic matter, and microbial activities. The experiment used a gas analyzer and gas chromatograph to measure samples under three conditions. The highest average flux rate was in fully enclosed vegetation (4.04 g CO2/m²/day), followed by not enclosed vegetation (4.01 g CO2/m²/day), and the lowest was 3.91 g CO2/m²/day. Results indicate that vegetation and urban parks reduce CO2 emission fluxes, with each area's vegetation state affecting soil and air temperature, pH content, and soil moisture. However, many aspects such as soil type and climate cognition can influence fluctuation of carbon fluxes in each condition.

Retinal Blood Vessel Segmentation Based on Encoder and Decoder Networks Using Weighted Cross Entropy Loss Function Dinial Utami Nurul Qomariah; Handayani Tjandrasa; Ade Irma Elvira
BULETIN ADALAH Vol. 9 No. 6 (2025)
Publisher : UIN Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/adalah.v9i6.44857

Retinal disease that has a major impact on human vision is diabetic retinopathy. Diabetic retinopathy is a disease caused by advanced diabetic mellitus. Early detection of the disease is very importance. An automated system that can recognize retinal blood vessel abnormalities is very useful for providing quick information to prevent further damage to the retina. In this study, we propose an automated system for segmenting the blood vessels in retinal fundus images using semantic segmentation based on pre-trained from VGG transfer learning and using median frequency balancing weights for the cross entropy loss function. The median frequency weights are to balance the importance of blood vessel and background pixels to get more accurate training results. The integration of encoder and decoder networks utilizing VGG transfer learning and semantic segmentation can segment retinal blood vessels with a sensitivity value of 85.48% using the DRIVE and STARE database.

URBAN AGRICULTURE: A SUSTAINABLE APPROACH TO LAND MANAGEMENT Ade Irma Elvira; Wiwit Ayu Pradana
BULETIN ADALAH Vol. 9 No. 6 (2025)
Publisher : UIN Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/adalah.v9i6.45132

Urban agriculture is farming conducted within urban communities and can be utilized as an efficient way to make use of land and natural resources. Urban areas currently consume 80% of the total energy produced globally and contribute over 70% to the total global greenhouse gases (GHGs) emissions. Urban agriculture can implement environmental sustainability by reducing GHG emissions and maintaining the air quality of cities. Various methods such as hydroponics, vertical farming, wall gardening, and aquaponics can be adopted to enhance agricultural productivity within limited urban spaces. Sustainable efforts need comprehensive policies regulating urban agriculture, including expanding household gardens, utilizing environmentally friendly technologies, and fostering stakeholder cooperation for urban agricultural development. This paper aims to highlight the importance of urban agriculture in achieving sustainable land management.

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search