Tuberculosis (TBC) is an dangerous disease and many people has been infected. One of many important steps to control TBC effectively and efficiently is by increasing case finding using right method and accurate diagnostic. One of them is to detect Mycobacterium Tuberculosis inside sputum. Conventional detection of Mycobacterium Tuberculosis inside sputum can need a lot of time, so digitally detection method of Mycobacterium Tuberculosis was designed as an effort to get better result of detection. This method was designed by using combination between digital image processing method and Neural Network method. From testing report that was done,Mycobacterium can be detected with successful value reach 77.5% and training error less than 5%.

The use of blockchain has received great attention in its adoption as a financial instrument in cryptocurrencies. This phenomenon needs to be considered in the sense not only as a form of financial transactions but also in other fields such as health, which is also a challenge for modern society. In addition, several government policies have also supported the provision of health services as a form of improving people’s living standards in the form of insurance. In this study, we try to design the system by using UML diagram and simulate the use of DApps offered by the Vexanium Ecosystem. For example, three basic activities between patients, doctors, and insurance will be simulated in the form of the transaction ledger. This method allows us to speed up the authentication process that previously needed to be performed for a long time with bureaucracy becoming the rule in smart contracts in a matter of minutes. The evaluation of this method will then be compared with eight existing blockchain projects. The result in healthcare processes is cost savings through increased automation, speed, standardization, and efficiency. All of this can be a preliminary analysis of its application in Indonesia, particularly related to the authentication and recording of medical records.

No abstract

Electrocardiograph (ECG atau EKG) merupakan alat diagnosis yang mengukur dan merekam aktifitas listrik jantung. Analisis sinyal EKG sering digunakan untuk mendiagnosis beberapa jenis kelainan jantung. Pada penelitian ini, kami merancang sistem jaringan syaraf tiruan untuk klasifikasi citra elektrikardiogram. Metode pemrosesan citra digunakan untuk ekstraksi fitur citra EKG dan proses klasifikasi menggunakan learning vector quantization. Beberapa data elektrokardiogram digunakan sebagai data pelatihan dan pengujian jaringan klasifikasi. Tiga jenis kelainan jantung dapat dideteksi oleh sistem. Hasil simulasi menunjukkan bahwa akurasi algoritma klasifikasi adalah sebesar 89% yang terdiri dari 9 normal, 4 bradikardi, 8 takikardi dan 7 aritmia.

No abstract