Claim Missing Document
Check
Articles

Found 2 Documents
Search

PREDIKSI PENYAKIT PARKINSON MELALUI DATASET REKAM SUARA DENGAN MENGGUNAKAN ALGORITMA DEEP NEURAL NETWORK Kristina Ronalita Nainggolan; Fanindia Purnamasari; Annisa Fadhillah Pulungan
Jurnal Minfo Polgan Vol. 12 No. 1 (2023): Article Research March 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v12i1.12985

Abstract

Penyakit Parkinson merupakan suatu gangguan sistem saraf kronis dan progresif yang dapat memengaruhi gerakan tubuh manusia. Pemeriksaan terhadap penyakit parkinson belum dilakukan seperti memeriksa keadaan medis pada umumnya, sehingga banyak pasien tidak menyadari bahwa mereka ternyata memiliki gejala penyakit Parkinson. Melalui pendekatan teknologi, penyakit parkinson dapat diperiksa melalui data rekam suara dari seorang pasien. Data rekam suara yang diperoleh dari dataset berupa data numerik yang kemudian perlu diproses. Data tersebut diproses dengan menggunakan pendekatan komputasi. Penelitian ini mengusulkan algoritma Deep Neural Network. Pada dataset yang diperoleh ditemukan ketidakseimbangan data sehingga diusulkan metode SMOTE (Synthetic Minority Oversampling Technique) yang digunakan sebagai teknik oversampling data. Selanjutnya diterapkan algoritma Deep Neural Network untuk memprediksi parkinson pada data tersebut dengan menggunakan parameter pada model seperti penggunaan aktivasi ReLu pada hidden layer, aktivasi sigmoid pada output layer, dropout, epochs 200, batch size 16, optimizer Adam dengan penggunaan learning rate sebesar 0.001, dan metrics accuracy, sehingga memberikan hasil akurasi sebesar 97%.
Implementation of Web Based E-Monitoring for Student Activities Record in SMK Swasta Medan Area 1 Ainul Hizriadi; Umaya Ramadhani Putri Nasution; Fanindia Purnamasari
ABDIMAS TALENTA: Jurnal Pengabdian Kepada Masyarakat Vol. 8 No. 2 (2023): ABDIMAS TALENTA: Jurnal Pengabdian Kepada Masyarakat
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/abdimastalenta.v8i2.11192

Abstract

SMK Medan Area 1 is one of the educational facilities that want to produce the best students to be able to become the best human resources in the future. The school is one of the secondary schools located in the city of Medan, North Sumatra province. The school provides various educational support facilities for its students so that they can learn to the fullest. For the sake of education progress, this Medan Area 1 Vocational School wants to take advantage of the available facilities and infrastructure, one of which is the internet. The school's need to quickly and easily supervise student activities and the curiosity of parents/guardians for information related to their sons and daughters makes a new need to continue to be able to unite all their children's activities at the school. These activities include attendance, tuition payments, notification of grades and violations committed by their sons and daughters. Therefore, a web-based monitoring application is needed to unify student activities that can be seen from anywhere, especially by parents/guardians. aims to provide convenience to teachers, especially counseling guidance (BK) teachers and web-based students in unifying several student activities including attendance, tuition payments, value notifications, and the method used in making applications carried out through five stages, namely: development problems , data collection for system requirements, system analysis and design, system implementation and implementation, and system testing