Claim Missing Document
Check
Articles

Found 27 Documents
Search

Penerapan Kombinasi Algoritma Sobel dan Canny (SoCan) dalam Identifikasi Citra Inversi Albatros Laysan Winanjaya, Riki; GS, Acmad Daengs; Anggraini, Fitri
Building of Informatics, Technology and Science (BITS) Vol 4 No 1 (2022): June 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1415.232 KB) | DOI: 10.47065/bits.v4i1.1660

Abstract

Utilizing an edge detection algorithm in an image will produce the edges of the image object. The aim is to mark the part that becomes the image's detail and correct the point of blurring of vision that occurs due to errors or the effects of the image acquisition process. This study aims to see the ability of the combination of Sobel and Canny edge detection algorithms (SoCan) to detect the inverted image. The image dataset used is the image of the Laysan Albatross, which consists of 10 original images and ten images that have been inverted based on the standard image dataset. The Laysan albatross is a large species of seabird found in the North Pacific. 99.7% of the total population is found in the Northwest Hawaiian Islands. The research dataset was obtained from the Caltech Vision Lab website http://www.vision.caltech.edu/datasets/cub_200_2011/ with dimensions of 500 x 271 pixels. Based on the analysis of 10 experiments carried out, the combination of the Sobel and Canny algorithm (SoCan) is not good at performing edge detection because it only has an average accuracy of 47.79% with an average accuracy error rate of 52.21%. Thus, in this case, the combination of the Sobel and Canny algorithms (SoCan) is not able to identify the Inversion Image
Teknik Klasifikasi C4.5 Dalam Menentukan Faktor Utama Kepuasan Nasabah Terhadap Pelayanan Klaim di PT Asuransi Central Asia Pematangsiantar Syahputra, Muhammad; Windarto, Agus Perdana; Winanjaya, Riki
Bulletin of Data Science Vol 1 No 1 (2021): October 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (640.58 KB) | DOI: 10.47065/bulletinds.v1i1.906

Abstract

Insurance claims can be made in accordance with important provisions in claim submission, such as claims in accordance with those stated in the policy, the policy is still valid (inforce), the policy is not in the waiting period and the claim is included in the coverage. Data Mining is a computer-aided process to explore and analyze large amounts of data sets and extract information and knowledge. Decision Tree is one of the Data Mining sections, with C4.5 algorithm is one of the classification methods that use decision tree representations where each nodes present attributes, branches represent the values ​​of attributes, leaves represent classes. and can be used to find dominant factors to find a decision, one of which determines the main factors of customer satisfaction with service claims at PT. Insurance Central Asia Pematangsiantar. It is hoped that the results will later be able to contribute greatly to PT. Insurance Central Asia Pematangsiantar in providing the best service to existing customers
Implementation of the Mamdani Fuzzy Method in Handling Room Availability in 2022 at Hotel Inna Parapat Nugroho, Muhammad Rizky Tri; Winanjaya, Riki; Susiani, Susiani
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 2 No. 2 (2023): June
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v2i2.2368

Abstract

This study aims to implement the Fuzzy Mamdani Method in handling room availability in 2022 at Hotel Inna Parapat. The Fuzzy Mamdani method is a mathematical approach to dealing with uncertainty and ambiguity in decision-making. This study collected and analyzed data regarding the number of hotel rooms, occupancy rates, and room demand during 2022 at Hotel Inna Parapat. Then, the Fuzzy Mamdani model was developed to predict room availability based on predetermined variables. The study results show that implementing the Fuzzy Mamdani Method can provide a more accurate prediction regarding room availability at Hotel Inna Parapat. The Mamdani Fuzzy Model can handle uncertainty and ambiguity in the data and provides membership values that provide a more precise picture of the actual situation. With the Fuzzy Mamdani model, Hotel Inna Parapat management can be more effective in optimizing room utilization, improving customer service, and anticipating high room demand in 2022. Implementing the Fuzzy Mamdani Method is important to handling room availability in 2022 at Inna Hotel Parapat. This approach is expected to help hotels and the hospitality industry make smarter, data-based decisions to deal with changing demands and dynamic business situations.
Model Prediksi Jaringan Saraf Tiruan Pada Anggaran Inventaris Di Pemerintahan Kota Pematang Siantar Tatahardinata, Jaya; Okprana, Harly; Winanjaya, Riki
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 8, No 1 (2023): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v8i1.614

Abstract

Inventory is the process of managing the procurement or inventory of goods owned by an office or company in carrying out its operational activities. Without an inventory a business activity will not be carried out, the existence of an inventory is very important. Office inventory is very important for the continuity of an agency. If one or more equipment is disturbed, it will definitely hinder the running of the company's economy which is usually in the form of irregular office inventory organization or lack of a system for inventorying office equipment. Therefore, the Neural Network is a powerful data model that is able to capture and represent complex Input-Output relationships, because of its ability to solve several problems, it is relatively easy to use, robustness of data input speed for execution, and initialization of complex systems. The method used in this research is the Backpropagation algorithm, which is a supervised method, with the help of the MATLAB application with Fletcher-reeves parameters. The research data used is Goods Identity Card data for 2018-2021. Based on this data, a network architecture model will be determined, including 1-10-1, 1-15-1, 1-20-1, and 1-30-1. From the five models, training and testing were carried out first and then obtained the results that the best architectural model was 1-10-1 with 0.01397196. So it can be concluded that the model can be used to predict inventory budget data, especially in Pematangsiantar City.
Optimisasi Fungsi Aktivasi pada Arsitektur LeNet untuk Meningkatkan Akurasi Klasifikasi Citra Tumor Otak Harliana, Harliana; Rahadjeng, Indra Riyana; Winanjaya, Riki
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.7108

Abstract

Brain hemorrhage is a critical medical condition that requires early and accurate detection to improve patient recovery outcomes. However, conventional image classification methods for brain hemorrhage still face limitations in terms of accuracy and efficiency. To address this issue, this study proposes optimizing the LeNet model using various activation functions—ReLU, Sigmoid, Tanh, and Swish—to enhance classification performance. Several optimization strategies were applied, including data augmentation techniques (flipping, rotation, shearing, rescaling) and fine-tuning of hyperparameters, to improve model generalization. Experimental results indicate that the model utilizing the Swish activation function achieves the most stable overall performance, with an accuracy of 55%, recall of 54%, precision of 54%, F1-score of 54%, and a ROC AUC value of 0.45. Although this performance is still below clinical application standards, the findings serve as an initial step toward exploring activation function optimization in CNN architectures. Further research is needed to significantly enhance classification accuracy and enable clinical viability.
Implementasi Data Mining Menggunakan Algoritma Apriori Dalam Menentukan Persediaan Barang : Studi Kasus: Toko Sinar Harahap Tarigan, Putri Mai Sarah; Hardinata, Jaya Tata; Qurniawan, Hendry; Safii, M; Winanjaya, Riki
Jurnal Janitra Informatika dan Sistem Informasi Vol. 2 No. 1 (2022): April - Jurnal Janitra Informatika dan Sistem Informasi
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25008/janitra.v2i1.142

Abstract

UMKM ialah kegiatan usaha kecil ekonomi rakyat yang berskala kecil dan dilindungi dari kompetisi usaha yang tak sehat dan tak setara. Wirausaha yang bergerak dibidang pertokoan memiliki prospek yang menjanjikan, karena dapat melayanin masyarakat dengan kategori ekonomi menengah kebawah dan ke atas serta bisa mempermudah masyarakat untuk berbelanja keperluan tiap hari tanpa harus belanja ke supermarket atau swalayan. Namun persediaan barang atau bahan kebutuhan yang tidak dilakukan secara optimal dapat menyebabkan kekosongan pada barang atau bahan kebutuhan tersebut. Hal tersebut juga terjadi pada toko sinar harahap yang sering mengalami kekosongan pada persediaan beberapa barang dan kebutuhan yang di cari oleh pelanggan, ini di akibatkan dari tidak adanya kebiasaan pengontrolan persediaan pada toko. Maka penelitian ini bertujuan untuk melihat barang dan kebutuhan apa saja yang dibutuhkan oleh pelanggan toko. Penelitian ini menggunakan beberapa variabel yaitu tanggal transaksi, nama produk serta jumlah penjualan/pembelian. Maka, dari hasil penelitian menggunakan algoritma apriori tersebut akan di dapat data nama barang yang paling banyak terjual untuk di jadikan sebagai antisipasi persediaan barang agar tidak mengalami kekosongan yang dapat menyebabkan pelanggan kecewa.
PENERAPAN DATA MINING ASOSIASI PADA PERSEDIAAN OBAT Febrivani, Elischa; Saifullah; Winanjaya, Riki
Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Vol. 4 No. 1 (2021): Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI)
Publisher : Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9767/jikomsi.v4i1.141

Abstract

Drug stock shortages or vacancies at a hospital will have a very bad impact on the success and smoothness of drug delivery transactions, the cause of a drug stock vacancy is the absence of information conveyed from the pharmaceutical installation to the supplier of the drug supplier. To prevent this, we need a system that can help suppliers of goods in order to know about the availability of drugs in pharmaceutical installations. Based on drug transaction data, this system is built using the Association method with Apriori algorithm which is a technique in data mining to find associative rules of combination between itemset. The calculation is done by determining support and confidence that will result in association rules, which can be used to determine what drug stocks are needed to prevent a drug stock gap.