Claim Missing Document
Check
Articles

Found 26 Documents
Search

Batik’s Pattern Recognition and Generation: Review and Challenges Dewa Made Sri Arsa; Anak Agung Ngurah Hary Susila; Desak Ayu Sista Dewi; Ni Putu Sutramiani; I Wayan Agus Surya Darma
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 10 No 2 (2022): Vol. 10, No. 2, August 2022
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2022.v10.i02.p04

Abstract

Batik is one of cultural heritage acknowledged by UNESCO. Intelligence system comes as one of solution to take parts on preservation programs of this heritage. This study explores the current state of the art in application of artificial intelligence on Batik images. This research provides a systematic investigation and present the current progress and hot issues in recognition and generation area for Batik images. Furthermore, this research also presents several Batik data sets and their state of the art. As a result of the review, we are projecting several future works in the discussion.
Handwritten Balinese Script Recognition on Palm Leaf Manuscript using Projection Profile and K-Nearest Neighbor Ni Putu Sutramiani; I Wayan Agus Surya Darma; Dewa Made Sri Arsa
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 10 No 3 (2022): Vol. 10, No. 3, December 2022
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2022.v10.i03.p02

Abstract

This paper presents a simple approach to the handwritten Balinese script characters recognition in palm-leaf lontar manuscripts. The Lontar manuscript is one of the cultural heritages found in Bali. Lontar manuscripts are written using a pengrupak, which is a kind of knife for writing on palm leaves. To give color to the results of the writing, candlenut is used so that the writing appears clear. In this paper, we apply the projection profile at the segmentation stage to get the handwritten Balinese script characters in the lontar manuscript. The palm leaf manuscript that we use is the Wariga Palalubangan palm leaf. The recognition process is carried out by implementing K-Nearest Neighbor in the recognition process. The recognition was made on the Wianjana script obtained from lontar manuscripts using 720 images consisting of 18 classes as dataset training. The test results showed that the level of recognition accuracy was obtained by 52% in the characters of handwritten Balinese scripts derived from lontar manuscripts and 92% in the characters of handwritten Balinese scripts on paper.
PELATIHAN MICROSOFT OFFICE DALAM UPAYA PENGUATAN KOMPETENSI GURU SEKOLAH DASAR I.M.S. Putra; D.P. Githa; I.P.A. Dharmaadi; I.M.S. Raharja; D.M.S. Arsa; A.A.N.H. Susila; N.P. Sutramiani; N.W.E.R. Dewi; D.P.S. Putri
Buletin Udayana Mengabdi Vol 22 No 2 (2023): Buletin Udayana Mengabdi
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/BUM.2023.v22.i02.p02

Abstract

Today's rapid development in the world of information technology causes almost all human work to become lighter and more effortless. One of them is the teacher's duties in teaching and giving grades. Applications already available on laptops or computers, such as Microsoft Office, can create more interactive teaching materials, create financial reports, or manage grades. However, most teachers who are familiar with laptops or computers can only operate the simple functions available in these applications, so the work that can be done is still limited. This service is carried out through training methods with material on using Microsoft Office applications (Word, Excel, PowerPoint) for teachers. The school being targeted is SD Negeri 7 Kesiman, whose environment is already fluent in technology but whose human resources are still limited in operating computers. The training material in the form of a Microsoft Office training module compiled by the service society team is used as a learning medium for teachers at SD Negeri 7 Kesiman. Evaluation of training activities used methods in the form of pre-test and post-test, in which the results showed that the ability of teachers at SD Negeri 7 Kesiman to understand the material had increased from before. These results also illustrate that the modules are arranged to make it easy to learn and conform to the needs of the features that the teacher often uses. Keywords : Competency, computer, information technology, Microsoft Office, teacher.
APLIKASI MARKETPLACE DENGAN FITUR SISTEM INFORMASI GEOGRAFIS Darma, Made Dwika Junata; Piarsa, I Nyoman; Arsa, Dewa Made Sri; Sutramiani, Ni Putu
JITTER : Jurnal Ilmiah Teknologi dan Komputer Vol 1 No 2 (2020): JITTER, Vol.1, No.2, December 2020
Publisher : Program Studi Teknologi Informasi, Fakultas Teknik, Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (658.934 KB) | DOI: 10.24843/jitter.v1i2.68985

Abstract

Perilaku konsumsi masyarakat Indonesia meningkat seiring perkembangan teknologi. Alvara tahun 2019 menunjukkan tingkat pencarian iklan di Indonesia pada tahun 2020 diproyeksikan meningkat menjadi US $ 130 milyar dibandingkan tahun 2016 (US $ 8 milyar). Kondisi tersebut berkaitan dengan peningkatan transaksi melalui marketplace. Meskipun demikian, pasar yang ada masih memiliki kelemahan, yaitu tidak adanya fasilitas pencarian lokasi toko online yang dituju. Hal tersebut menyebabkan pembeli kesulitan menemukan letak lokasi dari toko yang ingin ditemui. Masalah tersebut, maka dibuatlah aplikasi marketplace yang dilengkapi dengan fitur tambahan sistem informasi geografis yang memanfaatkan teknologi dari Google Maps API untuk memberikan informasi mengenai keberadaan suatu tempat usaha yang dapat diakses melalui smartphone dengan platform Android. Hasil uji coba implementasi terhadap 30 responden melalui kuesioner menunjukkan bahwa 72,6% responden sangat setuju aplikasi dapat diterapkan dengan baik, tampilan sudah sesuai (84,4%), dan dapat mempermudah menemukan lokasi dari toko atau iklan yang diinginkan (57,2%) ). Sistem diharapkan dapat diimplementasikan pada sistem selain Android. dan dapat mempermudah menemukan lokasi dari toko atau iklan yang diinginkan (57,2%). Sistem diharapkan dapat diimplementasikan pada sistem selain Android. dan dapat mempermudah menemukan lokasi dari toko atau iklan yang diinginkan (57,2%). Sistem diharapkan dapat diimplementasikan pada sistem selain Android.
Medical Costs Estimation Using Linear Regression Method Dwikasari, Ni Made Dita; Sutramiani, Ni Putu; Putri, Komang Sri Yanisa; Kusuma, Nyoman Tri Rahaditya; Pramana, Made Dimas Aldi Dwi; Darma, I Wayan Agus Surya
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 11 No 3 (2023): Vol. 11, No. 3, December 2023
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2023.v11.i03.p03

Abstract

Medical costs are a significant issue in the health sector. High healthcare cost lead to the need to anticipate financial risks for individuals and insurance providers. Therefore, medical cost data analysis is necessary to estimate future medical expenses. This research implements data mining techniques using Simple and Multiple Linear Regression methods to estimate medical costs. The dataset used consists of insurance claim data obtained from Kaggle, which includes attributes such as age, gender, body mass index, number of children, smoking habits, region, and medical charges. The research findings that Multiple Linear Regression outperforms Simple Linear Regression in estimating the provided dataset, with R2 value of 80% and lower ?? MSE and MAE values than Simple Linear Regression. The application of linear regression in insurance claim data analysis can provide significant benefits for patients, hospitals, and insurance providers. Overall, this research highlights the effectiveness of data mining techniques, specifically linear regression, in estimating healthcare costs.
Comparison Of Decision Tree, Linear Regression, and Random Forest Regressor Models for Predicting House Prices Sutramiani, Ni Putu
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 12 No 1 (2024): Vol. 12, No. 1, April 2024
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2024.v12.i01.p06

Abstract

A home is a basic requirement that offers comfort and security to its occupants. Because they are subject to price fluctuations, houses are also a potential option in an investing setting. As a result, buyers and investors require a system that can forecast house values. This study compares the effectiveness of decision trees, linear regression, and random forest regressors as models for predicting home prices. The dataset for predicting home prices was used in this study to conduct data exploration, pre-processing, modeling, and model comparison stages. The study's findings demonstrate that the random forest regressor offers the best prediction performance with lower assessment metrics, including MAE, MSE, RMSE, and R2 Score, making it the best option for predicting house prices and other financial outcomes.
Enhancing Breast Cancer Recognition in Histopathological Imaging Using Fine-Tuned CNN Darma, I Wayan Agus Surya; Sutramiani, Ni Putu
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 12 No 3 (2024): Vol. 12, No. 3, December 2024
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2024.v12.i03.p04

Abstract

Global Cancer Statistics reports that of the 2.3 million cases of breast cancer worldwide, 600,000 result in death. Factors contributing to breast cancer in women include both genetic and lifestyle influences. One method for recognizing breast cancer is through histopathology images. Recently, deep learning has gained significant attention in machine learning due to its powerful capabilities in modeling complex data, such as images. In this study, we classify breast cancer by training a Convolutional Neural Network (CNN) model on a dataset of histopathology images annotated and validated by experts, containing two classes. We propose an optimization strategy for CNN models to enhance breast cancer recognition performance, applying a fine-tuning strategy to MobileNetV2 and InceptionResNetV2 to evaluate CNN performance in classifying breast cancer within histopathological images. The experimental results demonstrate that the model achieves optimal performance with an accuracy of 96.22%.
Design and Development of Customer Relationship Management in a Construction Company Pertiwi, Ni Kadek Puja Ari; Sutramiani, Ni Putu; Wibawa, K Suar
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/qhkc3j28

Abstract

CV. Puspa Karya is a construction company that faces challenges in customer management and marketing activities. This study aims to design and implement a Customer Relationship Management (CRM) system using the Flectra framework to support marketing, sales, and customer‐service processes more effectively, with the specific objectives of improving both operational efficiency and customer satisfaction. The research employs the Accelerated SAP (ASAP) methodology, chosen for its systematic, result‐oriented approach that is well suited to projects requiring structured planning and rapid execution. ASAP was applied in five tailored phases: Project Preparation, Business Blueprint, Realisation, Final Preparation, and Go-Live & Support. The developed system was validated through User Acceptance Testing (UAT), achieving a final score of 167. User satisfaction was further assessed via the Post-Study System Usability Questionnaire (PSSUQ), yielding an overall mean score of 1.60 on a 1–7 scale (where lower scores indicate higher satisfaction): System Usefulness 1.55, Information Quality 1.66, and Interface Quality 1.61. These results exceed typical industry benchmarks for comparable systems. The implications include qualitative enhancements in customer‐service quality and quantitative gains in process speed and prospect‐tracking accuracy, leading to heightened operational professionalism, increased client trust, and stronger potential for customer loyalty.
Customer Segmentation for Optimizing Marketing Strategy at Hotel Puri Mesari Using the K-Means Clustering Method Ni Kadek Juniawatia; Ni Putu Sutramiani; Kadek Suar Wibawa
Jurnal Riset Multidisiplin Edukasi Vol. 2 No. 6 (2025): Jurnal Riset Multidisiplin Edukasi (Edisi Juni 2025)
Publisher : PT. Hasba Edukasi Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71282/jurmie.v2i6.382

Abstract

Hotel Puri Mesari Sanur menghadapi tantangan dalam mempertahankan tingkat okupansi dan retensi pelanggan, dengan tingkat retensi hanya 32,44%. Penelitian ini bertujuan untuk menganalisis segmentasi pelanggan menggunakan algoritma K-Means Clustering dan memberikan rekomendasi strategi pemasaran yang efektif. Tujuan tersebut adalah untuk memahami karakteristik pelanggan dan meningkatkan potensi pendapatan di tengah persaingan industri perhotelan yang ketat. Data reservasi hotel dari 2018 hingga 2024 dianalisis menggunakan K-Means Clustering, dengan validasi melalui Silhouette Score dan Elbow Method. Hasil analisis menunjukkan tiga cluster pelanggan: Cluster 0 mencakup pelanggan loyal dengan rata-rata 371 kunjungan dan pengeluaran moderat; Cluster 1 terdiri dari pelanggan dengan kunjungan rendah tetapi beragam asal negara; dan Cluster 2 merupakan segmen eksklusif dengan pengeluaran tertinggi dan durasi menginap terpanjang. Rekomendasi strategi pemasaran disusun menggunakan Marketing Mix 4P, lalu pihak manajemen hotel menguji rekomendasi tersebut dengan mengisi kuesioner skala Likert kepada mereka. Hasilnya, didapatkan rekomendasi strategi bagi setiap cluster yang sudah sesuai dan dapat diterapkan di hotel untuk memperkuat hubungan dengan pelanggan dan meningkatkan pendapatan.
Designing a Product Classification Dashboard for Marketing Strategy Using K-Nearest Neighbor Kadek Intan Cahya Putria; Anak Agung Ngurah Hary Susila; Ni Putu Sutramiani
Jurnal Riset Multidisiplin Edukasi Vol. 2 No. 7 (2025): Jurnal Riset Multidisiplin Edukasi (Edisi Juli 2025)
Publisher : PT. Hasba Edukasi Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71282/jurmie.v2i7.726

Abstract

The development of information technology has driven the use of sales data to support data-driven business decision-making. This study aims to design a dashboard to classify Orlenalycious Padangsambian's products using the K-Nearest Neighbor (K-NN) algorithm to determine more accurate marketing strategies. The methods used include collecting sales data from the Moka POS system, data preprocessing, classification using the K-NN algorithm with K=5, and visualizing the classification results in a Streamlit-based dashboard. The classification results divide the products into three categories: Highly Popular, Popular, and Fairly Popular. The proposed marketing strategy refers to the 4P Marketing Mix, where highly popular products are promoted intensively, popular products are pushed through advertising, and fairly popular products are evaluated or promoted through bundling. The resulting dashboard displays informative visualizations such as pie charts and bar charts to facilitate the analysis of sales trends and product performance. This study provides a solution for Orlenalycious to design more efficient and effective data-driven marketing strategies, as well as offering an easier way to monitor and evaluate product performance in real-time.