Claim Missing Document
Check
Articles

Found 37 Documents
Search

Support Vector Machine for Accurate Classification of Diabetes Risk Levels Sugiartawan, Putu; Wardani, Ni Wayan; Pradhana, Anak Agung Surya; Batubulan, Kadek Suarjuna; Kotama, I Nyoman Darma
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 19, No 3 (2025): July
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.107740

Abstract

This research explores the application of Support Vector Machines (SVM) for accurately classifying diabetes risk levels based on a publicly available dataset containing 768 instances and 9 attributes, including glucose levels, BMI, blood pressure, and insulin levels. The model's systematic development process involved data preprocessing, feature selection, and hyperparameter optimization to ensure robust performance. Results indicate an overall accuracy of 76%, with high precision and recall for the non-diabetic risk class, but relatively lower performance for the diabetic risk class, highlighting the challenges posed by class imbalance and overlapping data features. To address these issues, future research should incorporate advanced resampling techniques, refined feature engineering, and alternative machine learning models like Random Forest or XGBoost. This research underscores the potential of SVM as a valuable tool for early diabetes detection, offering healthcare professionals a reliable means to identify at-risk individuals and personalize intervention strategies. By bridging theoretical advancements and practical applications, the research contributes to enhancing predictive analytics in medical diagnostics, paving the way for improved patient outcomes and efficient public health management
Implementasi Naïve Bayes Pada Data Mining Untuk Mengklasifikasikan Penjualan Barang Terlaris Pada Perusahaan Ritel Wardani, Ni Wayan; Nugraha, Putu Gede Surya Cipta; Mahendra, Gede Surya
JST (Jurnal Sains dan Teknologi) Vol. 12 No. 3 (2023): Oktober
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jstundiksha.v12i3.38605

Abstract

Perusahaan ritel UD. Mawar Sari memiliki hingga 1,000,541 record data transaksi penjualan pada tahun 2019–2020 yang selama ini belum dipergunakan dengan baik. Data tersebut membutuhkan banyak ruang penyimpanan. Data tersebut juga belum dipergunakan secara efektif untuk tujuan apapun. Berdasarkan permasalahan tersebut, maka penelitian ini bertujuan untuk melakukan klasifikasi terhadap data transaksi penjualan untuk menemukan klasifikasi barang terlaris dengan data mining. Penelitian ini merupakan penelitian studi kasus yang menggunakan pendekatan penelitian kuantitatif. Metode yang digunakan adalah Naïve Bayes. Implementasi  penelitian ini menggunakan Rapidminer 9.0. Hasil penelitian dari klasifikasi data transaksi penjualan adalah klasifikasi produk yang laris dan tidak laris. Peneliti melakukan pengujian dengan 6043 data training dan hasil dari split validation terbaik pada split validation 0,7 dengan accuracy sebesar 93,82%. Hasil penelitian ini dapat digunakan dan berimplikasi baik untuk manajemen UD. Mawar Sari dalam pengambilan keputusan untuk menentukan suatu produk setelah mendapatkan hasil perhitungan data mining menggunakan metode Naïve Bayes.
Binary Classification of Exchange Rate Trends Using Logistic Regression Wardani, Ni Wayan; Pradhana, Anak Agung Surya; Kotama, I Nyoman Darma
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 7 No 4 (2025): June
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.218

Abstract

This study explores the use of logistic regression for binary classification of exchange rate trends, focusing on predicting upward and downward currency movements. Logistic regression, valued for its simplicity and interpretability, models the relationship between historical exchange rate data and macroeconomic indicators like interest rates, inflation, GDP growth, and trade balances. The methodology involves data collection, preprocessing, feature engineering, and model evaluation. Historical data is processed to address missing values, outliers, and noise, ensuring a robust dataset. Feature selection techniques, including mutual information scores and principal component analysis (PCA), identify key predictors, while L1 and L2 regularization enhance generalization. The model, implemented using Python's scikit-learn library, is optimized through grid search for hyperparameter tuning. Performance metrics, including accuracy, precision, recall, F1-score, and ROC-AUC, indicate strong predictive capability, achieving 99% accuracy in forecasting upward and downward trends. Logistic regression's interpretability aids decision-making, making it a valuable tool for financial forecasting. However, the study notes limitations, such as challenges posed by market volatility and geopolitical factors. Future research suggests incorporating sentiment analysis from financial news and social media, and exploring hybrid models combining logistic regression with ensemble methods or deep learning to improve performance under real-world conditions.
PENGEMBANGAN VIDEO TUTORIAL BEBASIS JAGAT KERTI DAN FUN LEARNING UNTUK MOTORIK HALUS DAN KARAKTER ANAK USIA DINI Putu Gede Surya Cipta Nugraha; I Nyoman Agus Suarya Putra; Ni Wayan Wardani
Jurnal Manajemen dan Teknologi Informasi Vol. 15 No. 2 (2025): Jurnal Manajemen dan Teknologi Informasi
Publisher : Fakultas Teknik dan Informatika Universitas PGRI Mahadewa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59819/jmti.v15i2.4941

Abstract

Digital technology in classroom learning can enhance teachers’ instructional resources by providing access to diverse verbal and nonverbal presentation modes. In early childhood education, developing fine motor skills often presents a significant challenge. This study explores the effectiveness of video tutorials as visual communication media, integrating the Balinese cultural concept of Jagat Kerti (a principle of universal harmony) and an engaging learning approach to develop fine motor skills and promote character development in young children. The video activities involve shaping objects with plasticine and narrating the folk tale The Monkey and the Turtle. The media production process is divided into three stages: pre-production, production, and post-production. Observations showed that before watching the video, children could recognize shapes and colors but struggled to manipulate plasticine. After watching the video and receiving teacher guidance, the children successfully formed objects like apples and turtles and understood the story’s moral messages. Testing with a small group of young learners confirmed that this educational media is highly suitable as a learning tool for early childhood education.
Enhancing Price Classification of Chili Using Gradient Boosting Machines Sugiartawan, Putu; Wardani, Ni Wayan
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 6 No 3 (2024): March
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.233

Abstract

This study explores the application of Gradient Boosting Machines (GBM) to enhance the classification and prediction of chili prices. The research uses a comprehensive dataset collected from various sources, including local markets, online platforms, and agricultural databases, covering multiple attributes such as chili type, region, harvest season, weather conditions, and demand-supply dynamics. The GBM model outperforms traditional machine learning algorithms, achieving an accuracy of 87%, with a high area under the ROC curve (AUC) of 0.91. Feature importance analysis indicates that harvest season and region are the most significant factors influencing price variations. The findings suggest that the GBM model provides reliable price predictions and insights into price-driving factors, offering valuable tools for stakeholders in the agricultural market. The study emphasizes the need for broader data sources and advanced techniques, such as time-series forecasting and XGBoost, to further improve chili price prediction models. These insights can help optimize supply chain management, price forecasting, and decision-making for producers, traders, and policymakers.
DEGISN OF A CHARGING SYSTEM USING AN ALTERNATOR TO SUPPORT THE PERFORMANCE OF THE REGENERATIVE BREAK SISTEM IN ELECTRIC VEHICLE Ma’sum, M. Arif; Wardani, Ni Wayan; Silaen, Debora Hotnauli
IJISCS (International Journal of Information System and Computer Science) Vol 8, No 2 (2024): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v8i2.1745

Abstract

The use of electric vehicles is now supported by a braking system capable of absorbing energy wasted from the braking process, known as regenerative brake. This research aims to optimize the use of the regenerative brake system by adding an alternator as a power generator to achieve more optimal charging. The voltage magnitude in the testing of the electric motorcycle NIU GOVA 03 obtained a generation voltage of 26VDC when traveling downhill for 100 meters at a speed of 45km/h. After designing the alternator for the electric motorcycle, the generation output increased to meet the battery charging voltage specification of 74VDC, suitable for application as a power source for a battery with a capacity of 60V14.7Ah. The braking portion before using the regenerative brake system over a distance of 100 meters took 4.8 seconds, but after implementing the regenerative brake system, the time decreased to 5.1 seconds. This indicates that the regenerative brake system, coupled with the alternator, can provide an effect in the form of decelerating the electric motorcycle by 8.7%.
PERANCANGAN MEDIA PEMBELAJARAN TENTANG SUMBER AIR UNTUK ANAK USIA DINI YANG BERLANDASKAN DANU KERTI I Nyoman Agus Suarya Putra; Dwi Novitasari; Mega Dewi Setyawati; Ni Wayan Wardani
Jurnal Manajemen dan Teknologi Informasi Vol. 13 No. 2 (2023): Jurnal Manajemen dan Teknologi Informasi
Publisher : Fakultas Teknik dan Informatika Universitas PGRI Mahadewa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59819/jmti.v13i2.3161

Abstract

Danu Kerti is an effort to preserve freshwater sources on land such as springs, lakes, rivers, and other springs. Springs are also very important for human life because the availability of clean water is very influential on daily human needs. Water is very important for people’s lives in Bali, even as a means of religious ceremonies. So it is very necessary to socialize about protecting water among the community because it is seen from the current condition of water in Bali which is very concerning which causes water pollution due to garbage and waste. Planting characters to care more about the environment, especially how to protect water, how to give thanks for water water can be used for daily needs such as drinking, bathing, and others, especially since early and through videos. From the results obtained after the children watched this learning video, there was a very good development of understanding about water source and their benefits and this media can also be recommended as an early childhood learning material.
ANALISIS KUALITAS LAYANAN DAN PENGGUNA APLIKASI OVO TERHADAP KEPUASAN PELANGGAN MENGGUNAKAN PIECES FRAMEWORK Ni Wayan Wardani; Ni Kadek Ayu Nirwana; Luh Putu Rara Ayu Ratnaningrum; Sita Haniyatus Salimah
Jurnal Manajemen dan Teknologi Informasi Vol. 13 No. 2 (2023): Jurnal Manajemen dan Teknologi Informasi
Publisher : Fakultas Teknik dan Informatika Universitas PGRI Mahadewa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59819/jmti.v13i2.3205

Abstract

The OVO application is an application that provides payment system services that can provide convenience in non-cash transactions, besides that the OVO application also opens access to digital financial products and services. OVO application which is a payment system used by various users. The diversity of these users will be an important point in assessing customer satisfaction because each customer has a different level of satisfaction. Users of the OVO application will assess customer satisfaction satisfied or dissatisfied, so that the existing system, will require further development in the future. One of the methods used in measuring the level of customer satisfaction is the pieces framework method which method has variables of performance assessment, information, economy, control, efficiency, and service. Researchers use questionnaires on 103 respondents who use the OVO application, INSTIKI students class of 2019, dissemination of this questionnaire through the Google form platform. The research results on the level of customer satisfaction showed the results of PUAS, with an average value above 4.06.
ANALISA PROSES BISNIS SIMPAN PINJAM PADA KSU JAYA MARUTI MENGGUNAKAN BUSINESS PROCESS IMPROVEMENT Ni Kadek Ayu Nirwana; Ni Made Mila Rosa Desmayani; I Kadek Adiana Putra; Ni Wayan Wardani; Dewa Ayu Giovany Angga Indrya
Jurnal Manajemen dan Teknologi Informasi Vol. 14 No. 1 (2024): Jurnal Manajemen dan Teknologi Informasi
Publisher : Fakultas Teknik dan Informatika Universitas PGRI Mahadewa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59819/jmti.v14i1.3752

Abstract

KSU Jaya Maruti is a form of all-business cooperative that runs various types of businesses, one of which is the savings and loan business. There are various problems and risks faced by KSU Jaya Maruti in carrying out the savings and loan business process. The problems that are often faced are in data management, such as the frequent occurrence of human errors when recording and unintentional changes to data, and difficulties in reconciling data at the time of closing the books and auditing. In this research, business process modeling (as-is) and (to-be) were created using Business Process Modeling Notation (BPMN) with the Business Process Improvement (BPI) method so that the KSU Jaya Maruti can be helped to face its problems. The results of this research recommendation are the modeling of ongoing business processes (as-is) and recommendations (to-be), as well as additional applications in the form of financial technology to carry out the recommended business processes. From the calculation of the distribution of questionnaires based on the results of the member questionnaire with respondents from 150 people, 76.89% of respondents stated that they agreed that the KSU Jaya Maruti implemented financial technology, and for the employee questionnaire with respondents from 18 people, 80.76% stated that they strongly agreed to implement financial technology.
PELATIHAN DAN PENDAMPINGAN PENGGUNAAN TEKNOLOGI INFORMASI UNTUK PENINGKATAN KAPASITAS PRAJURU DESA ADAT DI BALI Ni Wayan Wardani; I Putu Agus Eka Darma Udayana; Komang Redy Winatha; I Putu Yoga Indrawan; Putu Gede Surya Cipta Nugraha; Eddy Hartono; I Nyoman Agus Suarya Putra; Ni Made Mila Rosa Desmayani
Sewagati Vol. 1 No. 2 (2023): Sewagati
Publisher : Fakultas Teknik dan Informatika Universitas PGRI Mahadewa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (370.165 KB) | DOI: 10.59819/sewagati.v1i2.2734

Abstract

A traditional village in Bali is an institution that is responsible for managing and maintaining the sustainability of a traditional village in Bali. The development of information technology has developed so rapidly that even village officials must keep up with the development of information technology. However, in reality some village officials are not fluent in using information technology either in the form of Microsoft Word, Excel, Power Point, especially now that online meetings are also developing with many positive impacts. Based on these problems, community service was carried out by conducting Microsoft Word, Excel, Power Point training, and online meetings using the Zoom application. This training was conducted with the aim of increasing the skills of indigenous village communities in using information and communication technology. In this training, participants will be taught how to use Microsoft Word, Excel, and Power Point to create documents, process data, and make presentations. In addition, participants will also be taught how to use the Zoom application to conduct online meetings. This training is expected to provide benefits for indigenous village communities in improving their skills and productivity. Based on the evaluation results that have been carried out using the pre-test and post-test methods, in general there is an increase in the ability of village officials to operate the information technology material that has been provided in this community service.