No abstract

Para peneliti telah mencoba membantu kehidupan manusia dengan memanfaatkan citra satelit. Salah satu satelit yang dapat menyediakan data citra satelit adalah satelit National Oceanic and Atmospheric Administration (NOAA). Satelit ini secara khusus menangkap kondisi fisik laut dan atmosfer bumi dengan sisi negatif bahwa tidak semua data yang diperoleh berkualitas baik karena adanya intervensi frekuensi radio. Dalam tulisan ini, penggunaan kecerdasan buatan/Artificial Intelligence (AI) diterapkan untuk mengatasi masalah tersebut dengan membuat model pembelajaran mesin/Machine Learning (ML) menggunakan mesin yang bisa diajar dari google/Google’s Teachable Machine untuk mengklasifikasikan gambar dari perangkat frekuensi radio Weather Satellite Communication (WeSaCom) yang menangkap gambar menjadi mampu menyaring gambar. Data mining digunakan sebagai metodologi untuk mengumpulkan data citra dari satelit NOAA. Dataset citra dari satelit dianalisis dan dikelompokkan menjadi dua kelas, baik dan buruk. Kelas-kelas ini digunakan untuk membangun model dengan tujuan mengklasifikasikan data gambar yang diperoleh dari satelit NOAA melalui perangkat frekuensi radio WeSaCom. Hasilnya, ditemukan bahwa model Google Teachable Engine yang diterapkan pada perangkat WeSaCom mampu mengklasifikasikan data gambar dari NOAA dengan akurasi 96,72%.

Automatic Dependent Surveillance-Broadcast (ADS-B) is an aircraft backup radar device that transmits aircraft sensor information via radio frequency. This data can be used to detect aircraft changes that occur significantly or abnormally (anomaly). Anomaly detection in this study aims to reduce and prevent flight accidents by analyzing abnormal data on aircraft flights using the Deep Learning (DL) model. Bidirectional LSTM (Bi-LSTM) and Bidirectional GRU (Bi-GRU) models are proposed as DL models which are implemented on ADS-B data using data mining methods. The data is generated from the ADS-B device that records the plane crash incident and is stored on the Flightradar24 community server. Data containing sensor changes from anomalous aircraft movements are studied for predictability on other flight data. The class breakdown is divided into two, anomaly and normal, based on information on the time span of anomaly occurrences in the accident investigation report of each aircraft using the sliding window technique in the data mining methodology. In evaluation, the confusion matrix measurement method is used to predict predictive analysis of the tested data. The results of the model evaluation performance show that the Bi-LSTM proposed in this study has the best accuracy of 99.44% and the f1-score of 99.51% is slightly superior to the Bi-GRU model. The model in this study can be applied in the ADS-B device to detect aircraft movement anomalies and as material for reviewing technicians in periodic maintenance and measuring the accuracy of the ADS-B device used as a backup radar.

The COVID-19 pandemic in Indonesia has changed work patterns from those previously based on conventional to digitalization. One of the changes in the work pattern of digitalization is the shift in the behavior of using wet signatures on paper to digital signatures on electronic documents. The use of digital signatures cannot be separated from the strategic planning of information system (IS) and information technology (IT) strategy that refers to business strategies so that companies or agencies can compete. The need for planning in determining business strategy, IS/IT management strategy, and IT strategy before finding future application portfolios. Ward and Peppard were selected and used as a strategic planning method for information systems and information technology in this study. Business strategy can be found using internal and external analysis with strengths, weaknesses, opportunities, and threats (SWOT) with EFAS and IFAS matrix evaluation. The results were achieved in the strategic planning of the appropriate information system and information technology for agencies in achieving their business goals.

Significant population growth has been an issue lately. This means that crop production should be increased significantly to cater to the growing number of people. With less land to grow it on, changing climate and depletion of viable farmland, big data has been considered a promising approach to solve the problem. This main contribution of this study is to provide overview of the benefits of big data implementation in agriculture and the stakeholders involved by performing asystematic literature review on relevant papers. This study reveals that big data implementation brings benefits such as increase in revenue, support for sustainable agriculture, and support for data driven decision making. For successfulimplementation, stakeholders’ involvement from various sectors are needed.