Implementasi Fuzzy Expert System Mendeteksi Penyakit Parkinson Berbasis Mobile
Abstract viewed = 0 times
pdf (Bahasa Indonesia) downloaded = 0 times
Abstract
Parkinson's disease is a neurodegenerative disorder characterized by classic motor symptoms, namely bradykinesia, rigidity and tremor, where this disease attacks nerve cells gradually in the midbrain part which regulates the movement of the human body. This disease is one of the most common diseases found in old age with a prevalence of around 160 per 100,000 population. Among the general public knowledge about the diseaseparkinson considered to be minimal, as a result many sufferers parkinson which is not handled properly. Therefore the authors built an application to detect and provide information on Parkinson's disease withFuzzy Expert System. This application was built based on Android mobile to make it easier for users to operate it. In this research methodFuzzy Expert System aims to find out whether the patient has Parkinson's or not based on the input value of each symptom displayed. Symptom data were obtained from experts through interviews and appropriate literature. This system begins by entering the symptoms of Parkinson's disease that have been obtained from experts into the system. Symptoms included include: Tremor/vibration, Rigidity/Rigidity, Akinesia/Bradykinesia, Autonomic Dysfunction, Gait as if about to fall. After the symptoms are entered, the system will calculate the setFuzzy, each symptom is divided into 2 (two) criteria/sets, namely: rarely, and often. After forming the set Fuzzy, The system will match the rule base obtained from the expert. The results of this system detection whether the user has Parkinson's disease or not. In building the system the author uses the waterfall method, which means sequential and systematic. The database used is the MySQL database. Testing this research using the Black Box Testing method. From the research that has been done, this system has succeeded in achieving a percentage value of 85% for accuracy results based on 20 trials from respondents, there are 3 experiments that are not in accordance with expert opinion. On testingusability obtaining a percentage of 40% for very good and 60% for good, with these results showing that the expert system that has been built can run well and is easy for users to use. Keywords: Parkinson's Disease, Detecting, Fuzzy Expert System, Mobile
References
[2] Swandana, I., Raharjo, J., & Safitri, I. (2020). Identifikasi Penyakit Parkinson dengan metode Discrete Cosine Transform (DCT) dan Learning Vector Quantization (LVQ) Berdasarkan VGRF. E-Proceeding of Engineering, 7(2), 3606–3614.
[3] Novindra, Q. A., Alifah, F. G., & Syariafah, N. A. (2021). Epson (Early Detection for Parkinson Disease) Tinjauan Pustaka Disbiosis Gut Microbial Sebagai Potensi Deteksi Dini Parkinson Melalui Pemeriksaan Feses. Al-Iqra Medical Journal : Jurnal Berkala Ilmiah Kedokteran, 4(1), 1–8. https://doi.org/10.26618/aimj.v4i1.4980
[4] Bordelon, Y., & Keener, A. (2016). (2016). Parkinson’s Disease And Parkinsonism. Parkinsonism. Seminars in Neurology Doi:10.1055/s-0036-1585097, 36(04), 33.
[5] Azhar, S., Sari, H. L., & Zulita, L. N. (2016). Sistem Pakar Penyakit Ginjal Pada Manusia Menggunakan Metode Forward Chaining. Jurnal Media Infotama, 10(1), 16–26.
[6] Manik Prihatini, P. (2022). Metode Ketidakpastian Dan Kesamaran Dalam Sistem Pakar. Jurnal Ilmiah Teknologi Informasi, [S.l.], Nov. 2012. ISSN 2541-5832., vol 2.
[7] Astrid, T., Zebua, T., & Sihite, A. M. H. (2020). Sistem Pakar Diagnosa Penyakit Pada Sistem Pencernaan Kelinci Menggunakan Metode Fuzzy Expert System. Journal of Information System Research (JOSH), 1(3), 137–146. https://books.google.com/books?hl=en&lr=&id=PJHgDwAAQBAJ&oi=fnd&pg=PA137&dq=expert+system&ots=pX-C5QZ5_I&sig=MGp7R32lJ8p2u1HJMRiTM8zmcKE.
[8] Nurhayati, H., & Nugroho, F. (2012). Implementasi Fuzzy Expert System Untuk Diagnosis Penyakit Jantung. Implementasi Fuzzy Expert System Untuk Diagnosis Penyakit Jantung, 1–9.
[9] Athiyah, U., Handayani, A. P., Aldean, M. Y., Putra, N. P., & Ramadhani, R. (2021). Sistem Inferensi Fuzzy: Pengertian, Penerapan, dan Manfaatnya. Journal of Dinda : Data Science, Information Technology, and Data Analytics, 1(2), 73–76. https://doi.org/10.20895/dinda.v1i2.201
[10] Ferdiansyah, Y., & Hidayat, N. (2018). Implementasi Metode Fuzzy - Tsukamoto Untuk
Diagnosis Penyakit Pada Kelamin Laki Laki. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 2(12), 7516–7520.
