Claim Missing Document
Check
Articles

Found 38 Documents
Search

WHO ICD-10 BASED ONLINE DISEASE DIAGNOSIS FOR GENERATING DIGITAL MEDICAL RECORD APPLICATION DEVELOPMENT I Gusti Ngurah Lanang Wijayakusuma; Sagung Chandra Yowani
SINTECH (Science and Information Technology) Journal Vol. 5 No. 1 (2022): SINTECH Journal Edition April 2022
Publisher : Prahasta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/sintechjournal.v5i1.1040

Abstract

Medical Record is a medical document that contain history of patient’s disease also information about given treatments and medicines. Diagnosis of patient’s disease is one of content in Medical Record. Public health office recommends medical facility to write diagnosis into ICD-10 WHO standard. However, there are many of medical facility translate diagnosis into ICD-10 WHO standard manually. This manual way will make a lot of mistake or wrong translate result. This research will develop an online application to help the doctor to write patient’s disease diagnosis into ICD-10 WHO automatically. Doctors need to type the keyword of diagnosis name then selected diagnosis will automatically write into ICD-10 WHO standard. This application also can generate Digital Medical Record that can help medical facility to reopen or save Medical Record Data in a long time.
IMPLEMENTASI METODE ANALITICAL HIERARCY PROSES (AHP) PADA SISTEM PENENTUAN KREDIT LEMBAGA PERKREDITAN DESA (LPD) Made Agung Raharja; IGN Lanang Wijayakusuma
Jurnal Teknologi Informasi dan Komputer Vol 6, No 2 (2020): Jurnal Teknologi Informasi dan Komputer
Publisher : LPPM Universitas Dhyana Pura

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (678.51 KB)

Abstract

ABSTRACTA decision making is one of the problems faced almost every day, even at all times. In this study a Decision Support system will be developed by implementing the Analytic Hierarchy Process (AHP) method on credit analysis in the Village Credit Institution (LPD), which is one of the institutional elements of Pakraman Village that runs the financial function of Pakraman Village. Until now the LPD has the potential and has been proven in advancing the welfare of the village community itself. To foster public trust is not easy, because as it is known, there are many found unhealthy financial institutions. For the sake of smooth credit activities between LPDs as credit providers (creditors) and the community as credit applicants (customers), creditors need to assess and determine prospective customers before accepting or rejecting customers' credit requests. This needs to be done because the risk of non-payment of credit is quite high. So, a customer must meet the criteria that have been determined by the creditor to be able to get credit. The criteria used here are 5C, namely Character, Capacity, Collateral, Capital, and Condition. Based on the results of research that has been carried out, the system built has been able to be used to carry out the process of credit analysis and ranking prospective LPD customers based on the criteria attributes in determining LPD credit. It is seen from the results of testing on the needs of system functionality that has been fulfilled. With the AHP method, a decision support system is formed that can select prospective LPD credit recipients, and determine who is eligible and entitled to receive LPD Credit. The results of testing the system using blackbox testing are able to provide functionality based on system requirements analysis.Keywords : LPD, SPK-LPD , Analytic Hierarchy Process (AHP)ABSTRAKSuatu pengambilan keputusan merupakan salah satu masalah yang dihadapi hampir setiap hari, bahkan setiap saat. Pada penelitian ini akan dikembangankan suatu sistem Pendukung Keputusan dengan mengimplementasikan metode Analytic Hierarchy Process (AHP) pada analisa kredit di Lembaga Perkredian Desa (LPD) yang merupakan salah satu unsur kelembagaan Desa Pakraman yang menjalankan fungsi keuangan Desa Pakraman. Sampai saat ini LPD berpotensi dan telah terbukti dalam memajukan kesejahteraan masyarakat desa itu sendiri. Untuk menumbuhkan kepercayaan masyarakat tidaklah mudah, sebab seperti diketahui banyak sekali dijumpai adanya lembaga-lembaga keuangan yang tidak sehat. Demi kelancaran kegiatan perkreditan antara LPD sebagai lembaga penyedia kredit (kreditur) dengan masyarakat sebagai pemohon kredit (nasabah), kreditur perlu melakukan penilaian dan penentuan calon nasabah sebelum menerima atau menolak permintaan kredit nasabah. Hal ini perlu dilakukan karena resiko tidak terbayarkannya kredit cukup tinggi. Jadi, seorang nasabah harus memenuhi kriteria-kriteria yang telah ditentukan pihak kreditur untuk bisa mendapatkan kredit. Kriteria yang digunakan di sini adalah 5C, yaitu Character, Capacity, Collateral, Capital, dan Condition. Berdasarkan hasil penelitian yang telah dilakukan sistem yang dibangun sudah mampu digunakan untuk melakukan proses analisis kredit dan perangkingan calon nasabah LPD berdasarkan atribut kriteria dalam penentuan kredit LPD. Hal tersebut dilihat dari hasil pengujian terhadap kebutuhan fungsionalitas sistem yang telah terpenuhi. Dengan metode AHP, terbentuk suatu sistem pendukung keputusan yang dapat menyeleksi calon penerima kredit LPD, dan menentukan siapa yang pantas dan berhak untuk menerima Kredit LPD. Hasil pengujian sistem dengan menggunakan blackbox testing mampu memberikan fungsionalitas bedasarkan analisis kebutuhan sistem.Kata kunci : LPD, SPK-LPD , Analytic Hierarchy Process (AHP)
PENINGKATAN SDM DAN PEMASARAN UMKM KERAJINAN KAYU BERBASIS IPTEKS PADA UMKM KERAJINAN DESA PETULU UBUD Made Agung Raharja; Made Suyana Utama; Yohanes Kristianto Kristianto; I Gusti Ngurah Lanang Wijayakusuma
Jurnal Pengabdian Informatika Vol. 1 No. 3 (2023): JUPITA Volume 1 Nomor 3, Mei 2023
Publisher : Jurusan Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Usaha mikro, kecil, dan menengah (UMKM) dalam perekonomian nasional memiliki peran yang penting dan strategis. Saat ini di kecamatan Ubud hampir memiiki perusahaan perorangan atau yang tergolong UMKM yang paling banyak diantara daerah lainya. Dalam penerapan Program Udayana Mengabdi (PUM) ini terdapat mitra yang akan didampingi berlokasi di Desa Petulu, kecamatan Ubud, Kabupaten Gianyar, Provinsi Bali. Jenis UMKM yang dimiliki mitra tersebut adalah UMKM Kerajinan Kayu. Kegiatan Program Udayana Mengabdi (PUM) dengan tema peningkatan SDM dan pemasaran UMKM kerajinan kayu berbasis ipteks pada UMKM kerajinan desa petulu ubud melakukan beberapa kegiatan pendampingan dan pelatihan yang digunakan pada pemberdayaan UMKM untuk jenis usaha Kerajinan tanya dengan bahan dasar kayu adalah metode partisipatif yang diintegrasikan dengan kearifan lokal. Dengan metode yang partisipatif luaran yang diharapkan dari kegiatan PUM ini adalah: 1) Peningkatan keterapilan pemasaran UMKM dalam hal penggunaan teknologi informasi berbasis internet dengan menggunakan aplikasi online e-commers. 2) Peningkatan kemampuan manajemen usaha UMKM dan dalam hal pengelolaan keuangan serta pengelolaan aset UMKM. 3) Pengembangan usaha UMKM ke arah usaha ekonomi produktif yang berbasis teknologi informasi untuk menjaga keberlanjutan pendapatan dan diversifikasi usaha.
Klasifikasi Jenis Jerawat Berdasarkan Citra Menggunakan Convolutional Neural Network dengan Arsitektur MobileNetV2 Br Sebayang, Virna Dalira; Kusuma, I Gusti Ngurah Lanang Wijaya
JURNAL FASILKOM Vol. 14 No. 3 (2024): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v14i3.8202

Abstract

Jerawat merupakan permasalahan kulit yang kerap dihadapi remaja hingga orang dewasa secara global, di mana setiap jenis acne memerlukan penanganan yang spesifik. Metode yang diusulkan dalam penelitian ini mengklasifikasikan lima jenis jerawat menggunakan Arsitektur Convolutional Neural Network. Penelitian ini mengeksplorasi tiga skenario pembagian dataset berbeda: 70/30,80/20,90/10 untuk mengevaluasi kinerja dan generalisasi model. Metodologi mengadopsi arsitektur MobileNetV2 dengan transfer learning, yang terdiri dari lapisan termasuk MobileNetV2 sebagai model dasar, Global Average Pooling, Flatten, Dense Layer, Dropout, dan klasifikasi Softmax. Total dataset terdiri dari 350 gambar yang mewakili lima jenis jerawat: Acne Fulminans, Acne Nodules, Papule, Pustule, dan Fungal Acne, dengan 70 sampel per kelas. K-fold cross-validation digunakan untuk menilai performa model pada berbagai pembagian data. Hasil eksperimen menunjukkan kinerja model yang bervariasi di berbagai skenario, dengan akurasi klasifikasi berkisar dari 60% hingga 89% pada pelatihan dan 51% hingga 80% pada pengujian. Sistem klasifikasi CNN menunjukkan tingkat kinerja 89% untuk pelatihan dan 80% untuk pengujian. Skenario ketiga (pembagian 90/10) menunjukkan performa superior yaitu pada Fold-5, mencapai akurasi pengujian tertinggi sebesar 89% untuk pelatihan dan 80% akurasi pengujian. Tantangan dalam penelitian ini meliputi pengelolaan variasi pencahayaan gambar, kualitas gambar, dan keterbatasan data. Hasil menunjukkan bahwa arsitektur yang diusulkan dapat mengklasifikasikan jenis jerawat dengan tingkat akurasi yang cukup baik, meskipun masih terdapat ruang untuk perbaikan dalam generalisasi model.
Comparison of EfficientNet-B0 and ResNet-50 for Detecting Diseases in Cocoa Fruit Maylianti, Ni Putu; Wijayakusuma, I Gusti Ngurah Lanang; Arta Wiguna, I Putu Chandra
Journal of Applied Informatics and Computing Vol. 9 No. 1 (2025): February 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i1.8868

Abstract

Cocoa is a plant that is very susceptible to disease. One of the diseases that often attacks cocoa is black spots on the fruit. Detecting diseases in cocoa fruit is usually done manually by experts, which has limitations in providing information and is very expensive. this study proposes a model for detecting cocoa fruit diseases based on deep learning, namely convolution neural networks (CNN). This study compares CNN architectures, namely EfficientNetB0 and ResNet50 because these two architectures are very popular. EfficientNetB0 is known to be efficient in utilizing model parameters and the ability to achieve high accuracy, while ResNet50 uses Residual block recognition which allows deeper and more accurate model training. The dataset used is 3344 healthy cocoa fruit images, 943 black pod rot images and 103 pod borer images. From this study, the results for the accuracy of both methods are equally superior with an accuracy of 96% while for the precision of the EfficientNetB0 architecture is superior to ResNet50 with a value of 95.7% while for recall and f1-score ResNet50 is superior with a recall value of 94.7% and f1-score 93.3%. Based on the Confusion Matrix, it can be seen that ResNet50 is able to predict pod borer accurately so it can be concluded that in this study ResNet 50 is superior to EfficientNetB0. However, ResNet50 requires more parameters than EfficientNetB0 so ResNet50 requires a very large amount of data and when using a small amount of data EfficientNetB0 is more suitable for use.
Mutual Fund Performance Analysis Using Information Ratio, STJ Ratio and Value at Risk Ni Putu Leony Putri Paramita; Komang Dharmawan; I Gusti Ngurah Lanang Wijaya Kusuma
International Journal of Applied Mathematics and Computing Vol. 2 No. 1 (2025): January: International Journal of Applied Mathematics and Computing
Publisher : Asosiasi Riset Ilmu Matematika dan Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/ijamc.v2i1.66

Abstract

Measuring performance solely by relying on returns is probably not enough, it is important to consider both returns and risks. Some measurement methods that consider both of these factors are the Sharpe Ratio index, Treynor Ratio, Jensen Alpha, and Information Ratio. Risk analysis using Value at Risk Monte Carlo simulation is also important to determine the potential for extreme risks. The purpose of this study is to provide a good understanding of the performance and risk of mutual fund investments. Based on the performance results, Schroder is the most superior mutual fund, with the highest Information Ratio, Sharpe Ratio, and Jensen Ratio, indicating that they are able to generate good returns considering the risks taken. However, Schroder also has the highest VaR, meaning it has the potential for large losses in the worst market conditions. On the other hand, MNC is at the bottom in almost all performance methods, indicating poor performance with low returns and lower risks.
Application of Conditional Monte Carlo Simulation in Determining European Option Contract Pricing (Case Study on Toyota Motor Corporation (TM) Stock) Fransisca Emmanuella Aryossi; Komang Dharmawan; I GN Lanang Wijayakusuma
International Journal of Applied Mathematics and Computing Vol. 2 No. 1 (2025): January: International Journal of Applied Mathematics and Computing
Publisher : Asosiasi Riset Ilmu Matematika dan Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/ijamc.v2i1.97

Abstract

When making investment decisions, it is crucial for investors to consider various risks that may arise, both in the short and long term. One method to measure risk is through volatility. Volatility represents a statistical measurement of the degree of price variation over a specific period, expressed as volatility (σ) (Aklimawati & Wahyudi, 2013). This study aims to discuss the pricing of European option contracts using Conditional Monte Carlo simulation and the Black-Scholes method. The data used in this study is secondary data obtained from Yahoo Finance. The data consists of quantitative information, namely the monthly closing prices of Toyota Motor Corporation (TM) stock, spanning 5 years from July 1, 2019, to July 1, 2024, yielding 60 data points. In this research, the pricing of European call option contracts was calculated using Conditional Monte Carlo simulation and the Black-Scholes method. The study concludes that European option contract pricing can be determined using two methods: Conditional Monte Carlo simulation and the Black-Scholes method. Conditional Monte Carlo simulation can be employed to calculate European option prices in a structured manner, utilizing stochastic volatility estimated through the Ordinary Least Squares (OLS) method. The two methods yield differing option prices; Conditional Monte Carlo simulation produces lower option price estimates with relatively lower error values compared to the Black-Scholes method at every strike price. The lower estimates from Conditional Monte Carlo simulation are due to its consideration of stochastic changes in volatility, whereas the Black-Scholes method results in higher prices due to its assumption of constant volatility. The comparison demonstrates that Conditional Monte Carlo simulation provides cheaper price estimates under market conditions with non-constant volatility, despite requiring higher computational time compared to the Black-Scholes method. ,
Detection of Political Hoax News Using Fine-Tuning IndoBERT Jocelynne, Charlotte; Wijayakusuma, IGN Lanang; Harini, Luh Putu Ida
Journal of Applied Informatics and Computing Vol. 9 No. 2 (2025): April 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i2.8989

Abstract

Indonesia has experienced a surge in the spread of political hoax news, posing a potential threat to democratic and social stability. This study aims to develop a model for detecting political hoax news in the Indonesian language using IndoBERT, a language model optimized for Indonesian text. The dataset was sourced from Kaggle and comprises 20,928 factual news articles and 2,251 hoax news articles from major Indonesian media outlets, including CNN, Kompas, Tempo, and Turnbackhoax. The imbalance between factual and hoax news articles was addressed through undersampling, resulting in 1,302 samples for each class. The research stages include data collection, preprocessing, IndoBERT model training, and model evaluation. Results indicate that fine-tuning IndoBERT can detect political hoax news with an accuracy of 94.1% and an ROC AUC of 0.991, demonstrating high performance in accuracy and generalization capability. This research is expected to contribute to minimizing the spread of political hoax news in Indonesia and enhance media literacy among the public.
Comparison of Machine Learning Methods for Menstrual Cycle Analysis and Prediction Khairunisa, Mutiara; Putri, Desak Made Sidantya Amanda; Wijayakusuma, I Gusti Ngurah Lanang
Journal of Applied Informatics and Computing Vol. 9 No. 2 (2025): April 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i2.9076

Abstract

This study compares three machine learning methods—Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Decision Tree—for analyzing and predicting menstrual cycles. The dataset consists of 1,665 samples with 80 attributes encompassing information related to menstrual health. These methods were evaluated using accuracy, Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE) metrics. The results show that LSTM achieved the highest accuracy (91.3%), followed by CNN (88.9%) and Decision Tree (85.2%). LSTM excelled in capturing complex temporal patterns in menstrual cycle data, while CNN effectively identified key patterns, and Decision Tree offered interpretability despite lower performance. This study concludes that LSTM is the most effective model for menstrual cycle prediction. The findings highlight the potential for improved accuracy in reproductive health tracking, with future research opportunities to incorporate additional variables such as hormonal history and lifestyle factors, as well as a focus on data privacy.
Analisis Pemilihan Parameter pada Algoritma DBSCAN untuk Pengelompokan Titik Api di Indonesia Driyandita, Bernadeta; Kencana, I Putu Eka Nila; Wijayakusuma, I Gusti Ngurah Lanang
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 3 (2025): JPTI - Maret 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.703

Abstract

Kebakaran hutan, gambut, wilayah pertanian, maupun wilayah urban dan industri menjadi salah satu ancaman terbesar bagi lingkungan, menyebabkan kerusakan ekosistem dan kerugian ekonomi yang signifikan. Penelitian ini mengusulkan optimalisasi pengelompokkan titik api di Indonesia sebagai salah upaya pencegahan kebakaran dengan menggunakan algoritma Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Metodologi yang digunakan dalam penelitian mencakup pemrosesan data, pemilihan parameter tuning algoritma, dan evaluasi hasil klaster menggunakan metrik validasi internal yaitu Silhouette Coefficient (SC). Data penelitian diambil dari web FIRMS NASA berjumlah 12.708, dengan variabel yang digunakan yaitu longitude, latitude, bright_t31, brightness, fire radiative power, scan, dan track. Pada tahap pemrosesan dilakukan pembersihan dan standarisasi data memakai algoritma z-score. Selanjutnya percobaan klasterisasi dijalankan dengan mengubah-ubah nilai pada parameter epsilon (eps) sebesar 0.2, 2, 3, 4, 5, dan 10, yang dikombinasikan dengan nilai minimal point (MinPts) dari 2 sampai dengan 6.  Hasil pengelompokkan optimal yang ditemukan adalah pada saat percobaan dengan nilai eps 4 dan MinPts 4. Kondisi optimal tersebut menghasilkan 2 klaster dan 3 noise, dengan nilai SC sebesar 0.8022. Penelitian ini memberikan wawasan baru dalam pemetaan risiko kebakaran serta dapat digunakan untuk sistem pemantauan berbasis kecerdasan buatan.
Co-Authors Agustina, Ni Putu Dina Anak Agung Kompiang Oka Sudana Arta Wiguna, I Putu Chandra Astutik, Dian Br Sebayang, Virna Dalira Chandra, Veronica Celine Damayanthi, Ni Wayan Rita Desak Made Sidantya Amanda Putri Dian Astutik, Ni Putu Driyandita, Bernadeta EKA N. KENCANA Fransisca Emmanuella Aryossi G K Gandhiadi Gautama, IPW I Gusti Ayu Made Srinadi I Ketut Gede Darma Putra I ketut Gede Darma Putra I Ketut Restu Wiranata I KOMANG GDE SUKARSA I MADE EKA DWIPAYANA I Nyoman Widana I Putu Eka Nila Kencana I Putu Winada Gautama I Putu Winada Gautama I PUTU WINADA GAUTAMA I WAYAN SUMARJAYA IM Suyana Utama Isabel Divya Georgiana Walewangko Jocelynne, Charlotte Karina Maharani Bernis Karina Maharani Bernis Kencana, Eka N. Ketut Jayanegara Khairunisa, Mutiara Komang Dharmawan Kumaro, Leonard LUH PUTU IDA HARINI LUH PUTU IDA HARINI Made Ardika Mertha Putra Vaikuntha Made Ireina Dwiandra Divayanti Made Sudarma Made Sudarma Maharani, Made Andini Manurung, Mikael Triartama Maylianti, Ni Putu Minho Jo Minho Jo Ni Kadek Emik Sapitri Ni Kadek Jegeg Anastasya Dwipayanti Ni Luh Putu Suciptawati Ni Nyoman Bintang Marscelina Ni Putu Leony Putri Paramita Oka Sudana Pratama, Halim Meliana Pratiwi Tentriajaya, I Dewa Ayu Pradnya Putri, Desak Putri, Desak Made Sidantya Amanda Putri, Made Ayu Asri Oktarini Putu Veri Swastika Raharja, Made Agung Ratna Sari Widiastuti Riandika Fathur Rochim Sagun Chandra Yowani Sibannang, Maria Oktaviani Giska Siden, Hagia Sofia Swastika, Putu Veri Syahril Alamsyah Zainuddin Tentriajaya, I Dewa Ayu Pradnya Pratiwi Tobing, Charlotte Jocelynne L Ulfatun Farika Novitasari Widiastuti, Ratna Sari Yohanes Kristianto Kristianto