Anemia is a significant public health problem in female adolescents although intervention program has been established until present. One of the intervention programs, education on anemia is delivered by paper-based module. A scientific evidence is needed to evaluate the effectiveness of android application to prevent anemia through improvement in food and nutrient intake among female adolescents. The design studies used in this research, i.e. exploration, development (prototyping approach) and open label non-randomized trial. The location of this study was at six Muhammadiyah junior high schools in Depok since October 2015 to June 2016 with the phases of formative, pre-intervention, implementation for five months, post-intervention and follow-up for one month. Sample size calculation in this study was based on estimation means difference between two groups (228 subjects in android application group & 250 subjects in paper-based module group) with statistical analysis using General Linear model to evaluate the effectiveness of android application versus paper-based module on food & nutrient consumption and hemoglobin (Hb). This study showed that after controlling pre-intervention factors, there was significant different on the change in vitamin B12 intake. Other nutrients and Hb level between android application group and paper-based module group were not statistically different because of the influence factors from controlling factors, i.e. environment constraint & pre-intervention Hb. In addition to that, there was no statistically different in intention change after post-intervention and follow-up. This study revealed that adolescents using android application was better in determinant of behaviors, food & nutrient intake and Hb because they were more engaged in implementation intervention and more satisfied in experiencing the intervention. While paper-based module seemed to experience lower satisfaction. This can be interpreted that android application can be used for further intervention. Android application can be used as an education tool to prevent anemia among female adolescents. This effectiveness should optimize social media feature that female adolescents can have more interactive experience.
"
Cacar monyet muncul pada 2022 sebagai penyakit yang ditakutkan berpotensi sebagai pandemi selanjutnya. Cacar monyet adalah penyakit infeksi virus dari hewan (zoonosis) dan termasuk keluarga virus yang sama dengan cacar (smallpox, variola). Walaupun penyakit cacar monyet tidak lebih berbahaya dari COVID-19, diperlukan langkah pencegahan untuk mengurangi risiko penularan. Pendekatan machine learning dapat dilakukan dengan pengusulan penggunaan tiga arsitektur CNN, yaitu EfficientNetV2B1, MobileNetV3, dan NASNetMobile untuk mengklasifikasi cacar monyet dari citra lesi kulit. Ketiga model dilakukan transfer learning menggunakan pre-trained weights ImageNet bertotal 29 skenario dengan pemisahan data train dan test, dan melakukan augmentasi yang berbeda untuk menguji performa model. Skenario difokuskan pada peningkatan recall untuk mengurangi tingkat false negative pada prediksi cacar monyet. Penelitian ini juga membangun dataset yang terdiri dari empat kelas, yaitu cacar monyet, cacar air, campak, dan sehat dengan jumlah 40 hingga 100 foto per kelas. Citra dataset bersumber dari Kaggle dan web Kesehatan dan divalidasi kembali menggunakan Google Reverse Image. Dari eksperimen 29 skenario, didapatkan skenario dengan model yang optimal adalah MobileNetV3 versi minimalistic dengan recall 93,2%, dengan ukuran 7,6 MB, selisih recall dan validation recall 0,0035 dengan pemisahan data train dan test sebesar 70:30 dengan optimizer Adam 0,0001. Model dikonversi ke dalam format TensorFlow Lite dan disematkan ke dalam aplikasi Android yang dirancang menggunakan bahasa pemrograman Kotlin dan library UCrop untuk cropping citra yang diambil pengguna agar terfokus pada lesi kulit. Model membutuhkan rata-rata waktu inferensi 40 milidetik pada aplikasi Android.