Claim Missing Document
Check
Articles

Found 14 Documents
Search

ANALYSIS OF LAND SURFACE TEMPERATURE IN THE KRUENG ACEH WATERSHED USING GOOGLE EARTH ENGINE Khairunnisa, Yulia; Nazhifah, Sri Azizah; Amiren, Muslim; Syahreza, Saumi; Rusdi, Muhammad; Saputra, Kurnia; Putri, Andriani; Sukiakhy, Kikye Martiwi
CYBERSPACE: Jurnal Pendidikan Teknologi Informasi Vol 9 No 1 (2025)
Publisher : Universitas Islam Negeri Ar-Raniry Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22373/cj.v9i1.29076

Abstract

The constantly changing land surface temperature has implications for agricultural productivity and human health, therefore it is important to observe the land surface temperature to provide information about the characteristics and patterns of a region. The purpose of this research is to determine the changes and spatial patterns of land surface temperature distribution in the Krueng Aceh Watershed in 2013, 2018, and 2023. The method employed in this study involves utilizing the Google Earth Engine platform and MODIS imagery. Land surface temperature data from MODIS imagery is processed using JavaScript programming language, and the results are analyzed to obtain the distribution of land surface temperature. The study results indicate that the land surface temperature in the Krueng Aceh Watershed was 29,11℃ in 2013, increase to 29,5℃ in 2018, and then decreased to 29,19℃ in 2023. The Krueng Aceh Watershed in 2013, 2018, and 2023 exhibits similar spatial patterns and distributions of land surface temperature, with areas in Banda Aceh City experiencing higher temperatures compared to those in Aceh Besar District, which exhibit varying temperatures.
Uji Kelayakan Sistem Informasi Berbasis Web Pada Kasus Penyakit Mulut dan Kuku Nazhifah, Sri Azizah; Basri, Fazil; Muslim, Muslim; Putri, Andrini
The Indonesian Journal of Computer Science Vol. 13 No. 3 (2024): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i3.3967

Abstract

Foot and Mouth Disease (FMD) is a viral infection in animals that is contagious and acute. However, public access to information and visualization of the spread of FMD and vaccination in Nagan Raya District is still limited. The reporting of FMD cases by the public still relies on village authorities, leading to inaccuracies in information and field validation constraints. Additionally, difficulties in registering livestock vaccinations are caused by inaccuracies in data and livestock location, hindering the Animal Husbandry Department in providing doses and determining the route to these locations. Therefore, this research aims to build a WebGIS that includes visualization of FMD spread, FMD case reporting, and vaccination registration. This WebGIS is developed using Laravel and Leaflet, tested with validation, reliability, and usability questionnaires. Users include the general public, the Animal Husbandry Department, and medical professionals. The results show that the WebGIS has an 89.3% feasibility percentage and is highly suitable. It can facilitate access to FMD information and visualization and streamline reporting and vaccination registration.
PERFORMANCE ANALYSIS OF MACHINE LEARNING AND INDOBERT IN CLASSIFYING SENTIMENTS ON INDONESIA'S FREE NUTRITIOUS MEAL Maulyanda; Nazhifah, Sri Azizah; Pane, Syafrial Fachri; Irvanizam, Irvanizam
CYBERSPACE: Jurnal Pendidikan Teknologi Informasi Vol 10 No 1 (2026)
Publisher : Universitas Islam Negeri Ar-Raniry Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22373/cj.v10i1.33886

Abstract

Natural Language Processing (NLP) is a branch of artificial intelligence that is widely used to analyze whether a sentence contains positive, negative, or neutral sentiment, particularly in the context of expressing opinions in the online environment. This study compares several models to identify the most optimal one, namely Naïve Bayes, Support Vector Machine (SVM), XGBoost, and IndoBERT. The dataset used in this research was obtained from Kaggle and consists of 5,644 data points in the neutral class, 2,934 data points in the positive class, and 2,606 data points in the negative class. Prior to model implementation, the dataset underwent a preprocessing stage that included case folding, cleansing, tokenization, stemming, and stopword removal. Subsequently, the data were trained using the four aforementioned methods. The results indicate that Naïve Bayes achieved an accuracy of 75%, SVM reached 79%, XGBoost obtained 76%, while IndoBERT achieved the highest accuracy at 85%. Therefore, it can be concluded that, using this dataset, IndoBERT performed sentiment classification very effectively.
SIMULATION-DRIVEN METHOD FOR WATER COVERAGE MONITORING FROM MULTI-SENSOR SATELLITE IMAGERY Putri, Andriani; Huang, Chih-Yuan; Tseng, Kuo-Hsin; Lin, Tang-Huang; Maghfirah, Hayatun; Nazhifah, Sri Azizah; Ridho, Abdurrahman; Mutia, Cut
CYBERSPACE: Jurnal Pendidikan Teknologi Informasi Vol 10 No 1 (2026)
Publisher : Universitas Islam Negeri Ar-Raniry Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22373/cj.v10i1.34380

Abstract

Monitoring water coverage in intertidal zones is challenging due to the lack of satellite sensors that simultaneously provide both high spatial and high temporal resolution. Landsat offers detailed spatial information but is limited by its 16-day revisit cycle, whereas Himawari-8 provides frequent observations but at coarse spatial scales. Existing multi-sensor fusion approaches, such as STARFM and ESTARFM, attempt to bridge this gap but rely on the assumption of linear or abrupt land cover changes, which is inadequate for capturing the gradual and non-linear dynamics of tidal environments. This study proposes a simulation-driven method to enhance water coverage monitoring by generating reference images that represent varying water height conditions. The approach integrates normalized Landsat OLI and Himawari-8 AHI imagery with digital elevation and tidal models to interpolate Modified Normalized Difference Water Index (mNDWI) values. Through linear interpolation, synthetic reference images are produced for low, medium, and high-water height scenarios, filling temporal gaps and providing additional input for fusion-based monitoring. Results from the Hsiang-Shan Wetland demonstrate that simulated reference images contribute more significantly to accurate water mapping than Himawari-8 data alone. The method improves temporal continuity, enhances the representation of tidal dynamics, and reduces discrepancies in fused outputs. Although the accuracy depends on DEM and tidal model quality, the findings highlight the potential of simulation-driven approaches to strengthen water monitoring frameworks. This method can be extended to support applications in flood mapping, wetland management, and coastal conservation.