cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ichwanul Muslim Karo Karo
Contact Email
cs@unimed.ac.id
Phone
+6285262688968
Journal Mail Official
jids@unimed.ac.id
Editorial Address
Gedung 77, FMIPA di Jalan Willem Iskandar, Pasar V Medan Estate, Percut Sei Tuan, Deli Serdang
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Informatics and Data Science (J-IDS)
Published by Universitas Negeri Medan
ISSN : -     EISSN : 29640415     DOI : https://doi.org/10.24114/j-ids.xxx
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management
Journal of Informatics and Data Science (J-IDS) is a scientific journal managed by the Computer Science Study Program, Faculty of Mathematics and Natural Sciences, Medan State University, Indonesia which contains scientific writings on pure research and applied research in the field of computer science and data science as well as summarizing general developments in related theories, methods and applied sciences. Focus dan Scope J-IDS covers: Artificial Intelligence Science Computation Data Mining Data Science Big Data Natural Language Processing Computer Vision Expert System Text and Web Mining Parallel Processing
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 33 Documents
 1   2   3   4 
Analisis Survival Model Regresi Cox terhadap Laju Kesembuhan Pasien Penyakit Dispepsia di RSUD Kabupaten Aceh Tamiang NURUL KHIANA SAFITRI
Journal of Informatics and Data Science Vol 1, No 1 (2022): Vol 1, No 1 (Juni 2022)
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v1i1.38521

Abstract

Analisis survival merupakan metode untuk menganalisis data berdasarkan waktu. Penelitian ini menganalisis faktor laju kesembuhan pasien dispepsia RSUD Kabupaten Aceh Tamiang menggunakan regresi cox proportional hazard. Populasi penelitian berupa rekam medis pasien dispepsia rawat inap di RSUD Kabupaten Aceh Tamiang pada Januari-Desember 2018, sedangkan sampel diambil sebanyak 87 pasien. Hasil menunjukkan faktor yang mempengaruhi laju kesembuhan pasien adalah infeksi Helicobacter pylori, dimana laju kesembuhan pasien yang tidak terinfeksi Helicobacter pylori 6,019 kali lebih cepat dari pasien terinfeksi Helicobacter pylori yang berarti pasien penderita penyakit dispepsia yang terinfeksi Helicobacter pylori memiliki laju kesembuhan lebih lama dari pasien tidak terinfeksi Helicobacter pylori.
Application of the Naïve Bayes Algorithm for Web-Based Classification of Family Hope Program Beneficiaries Nafisa, Anti Nada; Al Idrus, Said Iskandar
Journal of Informatics and Data Science Vol 2, No 2 (2023): November
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v2i2.47256

Abstract

The government realizes the importance of the problem of poverty by making various efforts, one of which is holding social assistance programs for the poor. One of the government policies is the Family Hope Program (PKH). The situation in the community indicates that those who receive PKH assistance from the government usually use the assistance to meet the health needs of their families, schools and daily needs, which are generally consumptive. The process of processing PKH beneficiary data in the Timbang Deli sub-district is still done manually, therefore this study aims to carry out data processing with the Naïve Bayes classification by creating a system to make it easier for officers in the Timbang Deli sub-district to determine PKH beneficiaries. The method used in this study is the Naive Bayes classification method. The variables used in this study were the head of the family, number of dependents, occupation, income, number of cars, number of motorcycles, status of residence, and condition of the house. The data in this study were 100 data from PKH beneficiaries and non-recipients of Timbang Deli Village, 80 as training data, and 20 as testing data. Based on the results of a study of 20 test data for recipients and non-recipients of PKH assistance in Timbang Deli Village, Medan Amplas District, the accuracy of the truth is 80% where there are 16 data that have values according to the test data, and 4 data that have values that do not match the test data.
PENGEMBANGAN SISTEM INFORMASI GEOGRAFIS BERBASIS WEB UNTUK PENYEBARAN PENYAKIT COVID-19 MENGGUNAKAN METODE K-MEANS (Studi Kasus : Kabupaten Deli Serdang) Syasa Anbar Pratiwi
Journal of Informatics and Data Science Vol 1, No 2 (2022): Vol 1, No 2 (2022)
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v1i2.42424

Abstract

Tingkat penyebaran kasus Covid-19 di Indonesia diketahui masih cukup tinggi. Penambahan kasus Covid-19 juga belum mengalami penurunan yang signifikan. Persebaran yang juga sudah menyebar hampir ke seluruh wilayah di Indonesia, salah satunya di kabupaten Deli Serdang. Adanya 22 kecamatan di Deli Serdang yang menjadi persebaran kasus Covid-19. Untuk memudahkan dalam mengetahui informasi persebaran Covid-19 maka perlunya peneliti untuk menentukan tingkat persebaran terkait penyebarannya dalam menentukan wilayah mana saja yang beresiko. Untuk mengetahui informasi penyebaran Covid-19 maka di butuhkanlah sebuah Sistem Informasi Geografis untuk memetakan wilayah yang terdeteksi tingkat penyebarannya.
IMPLEMENTASI METODE BACKPROPAGATION UNTUK MEMPREDIKSI CURAH HUJAN DI PROVINSI SUMATERA UTARA Rinjani Cyra Nabila
Journal of Informatics and Data Science Vol 2, No 1 (2023): VOL 2, NO 1 (2023): VOL 2, NO 1 (2023)
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v2i1.42986

Abstract

Tingkat kerugian masyarakat yang tinggi disebabkan oleh terjadinya bencana alam. Hal ini dikarenakan minimnya informasi yang diterima masyarakat tentang potensi bencana di sekitar mereka. Dengan demikian, kesadaran masyarakat akan tanggap bencana sangat rendah. Oleh karena itu, informasi cuaca sangat penting untuk kelancaran aktivitas dan aktivitas manusia, termasuk melihat besarnya curah hujan. Adapun  tujuan dari penelitian ini untuk mengetahui model terbaik yang digunakan untuk memprediksi curah hujan di Provinsi Sumatera Utara dan mengetahui trend curah hujan pada tahun yang akan datang. Data yang diambil pada penelitian ini merupakan data time series curah hujan yang terdapat di 6 stasiun di Provinsi Sumatera Utara pada 10 tahun terakhir yang meliputi Stasiun Meteorologi Sibolga, Stasiun Meteorologi Aek Godang, Stasiun Meteorologi Silangit, Balai Besar Meteorologi, Klimatologi dan Geofisika Wilayah I Medan, Stasiun Klimatologi Deli Serdang, dan Stasiun  Meteorologi Binaka. Penelitian ini menggunakan metode terbaik dalam memprediksi yaitu metode backpropagation. Hasil yang sudah dilakukan pada data curah hujan Provinsi Sumatera Utara didapat model terbaik dengan iterasi optimal sebesar 1000 iterasi, pada uji coba learning rate didapat learning rate optimal 0,1 dan mendapatkan jumlah node hidden 5 yang terbaik. Pada proses pengujian didapat hasil MSE 0,047 dan 0,022 dan nilai RMSE 0,0022 dan 0,00049.Kata Kunci: jaringan syaraf tiruan, Backpropagation, Prediksi, Curah Hujan
Forecating Composite Stock Price Index (CSPI) Using Long Short Term Memory (LSTM) Intan Elprida Silaban
Journal of Informatics and Data Science Vol 1, No 1 (2022): Vol 1, No 1 (Juni 2022)
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v1i1.38571

Abstract

The Composite Stock Price Index (CSPI) is an index that displays developments the whole movement of the company's share price in the stock market which refers to the Indonesia Stock Exchange (IDX). Before considering investment, investors can predict the Indonesian stock market is up and down by CSPI analysis. The main objective of this research is to propose forecasting model of CSPI using Long Short Term Memory (LSTM). The performance of LSTM model measured by Root Mean Square Error (RMSE). The results showed that the best LSTM models is model with number of neuron in hidden layer and epoch (iterations) were 10 and 10, respectively. The RMSE values achieved from the LSTM models for testing data is 0,0633. Visually, the prediction graph is almost similar with original data.
Detection of Participants Facial Expressions in Video Conference Using Convolutional Neural Network Algorithm Karimuddin Hakim Hasibuan; Hermawan Syahputra
Journal of Informatics and Data Science Vol 2, No 2 (2023): November
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v2i2.49060

Abstract

Purpose: The purpose of this research is to develop an architecture based on the Convolutional Neural Network (CNN) algorithm to detect facial expressions during video conferences. The goal is to address the problem of understanding participants' emotions and expressions during online video conferencing sessions. The aim is to create a system that can analyze facial expressions in images and determine the corresponding emotions.Methods/Study design/approach: Data was collected by capturing facial expression images from 10 students using a webcam. Preprocessing techniques, such as cropping, converting images to grayscale, and data augmentation, were applied to ensure data variation. The CNN model was trained using the processed data and evaluated using test data (a subset of the dataset), new data (external data) and video conference recording. Result/Findings: The CNN model achieved a high training accuracy of 97.5% using an image size of 128x128 and 2000 epochs. The model architecture consists of 2 Conv2D layers, 3 BatchNormalization layers, 2 MaxPooling layers, 2 dropout layers, 1 flat layer, 1 dense layer, and 1 output layer. When tested on facial expression data, the model achieved with 97,5% accuracy on the training data and 93,33% accuracy on the test data. The model was also able to detect the facial expressions of participants in the video conference. Novelty/Originality/Value: The novelty of this research lies in developing a CNN-based system to detect facial expressions in video conferences by analyzing facial images. This approach addresses the challenge of understanding participants' emotions and expressions during online video conferencing sessions, which can contribute to better communication and interaction among participants.
Klasifikasi Gambar Catat Meter Menggunakan Convolutional Neural Network Tias Novika Haryanti
Journal of Informatics and Data Science Vol 1, No 2 (2022): Vol 1, No 2 (2022)
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v1i2.42454

Abstract

Listrik merupakan kebutuhan pokok manusia dalam menjalankan setiap kegiatan, yang pemakaiannya dapat diukur menggunakan KWH Meter. Di Indonesia pelanggan listrik dibagi menjadi dua yaitu Prabayar dan Pascabayar. Pelanggan listrik pascabayar memerlukan pencatatan angka yang tertulis pada KWH meter untuk mengetahui rupiah tagihan listrik yang harus dibayarkan. Dalam pelaksanaan pencatatan angka tersebut, tidak jarang ditemukan kendala seperti pagar rumah pelanggan yang terkunci sehingga petugas tidak berhasil memotret angka stan meter. Oleh karena itu PLN rutin melakukan validasi atas keseluruhan data pencatatan meter. Penelitian ini bertujuan untuk memvalidasi data catat meter yang berupa gambar dan diklasifikasikan kedalam tiga kelas menggunakan algoritma Convolutional Neural Network (CNN) dengan arsitektur Resnet34. Pada penelitian ini mendapat hasil tingkat akurasi tertinggi sebesar 97.50%. Kata Kunci: Listrik, KWH, Klasifikasi, CNN, Resnet34.
Performance Comparison of VGG16, VGG19 and Alexnet Pre-Trained Transfer Learning Architecture Models in the Convolutional Neural Network Algorithm in Classification of Lung Disease Harahap, Fahri Aulia Alfarisi
Journal of Informatics and Data Science Vol 3, No 1 (2024): JUNE 2024
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v3i1.51163

Abstract

This study aims to comprehend the performance of transfer learning architectures (VGG16, VGG19, and Alexnet) in a Convolutional Neural Network for classifying lung diseases. Another objective is to determine the most superior transfer learning approach in this classification scenario. The dataset consists of 5 classes: normal lungs, pneumonia, bronchopneumonia, tuberculosis, and bronchitis. The data was sourced from Sinar Husni Deli Serdang Hospital through the radiology laboratory. The dataset was divided 80:20 for training and testing, with hyperparameters including a batch size of 32, 50 epochs, and optimization using Adaptive Momentum Optimization with a learning rate of 0.001. The research findings reveal that the VGG19 transfer learning architecture achieves the best performance with an accuracy of 59.17%, precision of 62%, recall of 59.2%, and an f-1 score of 58.8%. VGG16 ranks second with an accuracy of 55.83%, precision of 58%, recall of 55.8%, and an f-1 score of 55.2%. Alexnet has an accuracy of 49.17%, precision of 53.2%, recall of 49.2%, and an f-1 score of 50.6%. In an external test with 50 data points, VGG16 attains an accuracy of 54%, VGG19 scores 42%, and Alexnet records 46%. These models perform better in classifying normal lungs and tuberculosis compared to pneumonia, bronchopneumonia, and bronchitis. Analysis of lung image data demonstrates that homogeneity of RGB pixel values within a class supports transfer learning performance in classification. Conversely, heterogeneity in RGB pixel values can diminish the evaluation of that class.
Analysis of Prediction of Glove Production Quantity Using Sugeno's Fuzzy Logic (Case Study: PT Medisafe Technologies) R Simaremare, Martin Hans
Journal of Informatics and Data Science Vol 2, No 2 (2023): November
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v2i2.50839

Abstract

Purpose: These days there are often problems in the world sometimes have uncertain or vague answers. Therefore, fuzzy logic is one method for conducting such uncertain analysis. This thesis discusses the application of fuzzy logic Analysis of Prediction of Glove Production Quantities using the Sugeno method. The problem that is solved is to predict or predict the amount of production of goods  because some workers in the company predict production figures by filling or the minds of the workers themselves based on the previous year's production output dataStudy method/design/approach: The first step for this study is to determine the input and output variables that are firm sets and then convert each variable into a fuzzy set consisting of Little, Medium, and Many by fuzzification process. It then processes the fuzzy set data through base rules defined by the minimum method to retrieve the smallest membership degree value previously calculated through the membership function representation. And the last one is the Sugeno Method Defuzzification, which is to find the value of the average weight centrallyResults/Findings: Based on prediction analysis calculations using Stock and production data from December 2018 to January 2023, the predicted amount obtained in the following year is higher than the actual production amount in the previous year. In January 2022, the actual production output obtained from PT. Medisafe Technologies amounted to 181,822,894 pcs, while the prediction results from calculations using the Sugeno fuzzy logic model amounted to 327,147,796 pcs. The error accuracy value using MAPE is 1.66%, which means that the accuracy of truth is 99.4%. So forecasting the amount of production using the Sugeno fuzzy logic model is very good for the company.Novelty / Originality / Value: The novelty of this study lies in the development of a model using the fuzzy sugeno method to predict the amount of glove production. This approach discusses to forecast the number of glove production in a company per month interval based on data on the amount of production in the previous year  as an output  variable and raw material inventory data as an input variable.
EXPERT SYSTEM FOR IDENTIFYING DENTAL DISEASES USING THE DEMPSTER-SHAFER METHOD BASED ON ANDROID khatulistiwa, jamrud; arnita, arnita
Journal of Informatics and Data Science Vol 3, No 1 (2024): JUNE 2024
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/j-ids.v3i1.51022

Abstract

The ability of an expert system to identify symptoms is not as optimal as that of a specialist because there are still uncertainties that can cause errors in identification. Therefore, the Dempster-Shafer method is used to calculate expert system uncertainty. This dental disease identification system is designed as an Android application. Then, system accuracy is tested by comparing system identification results with test data from medical records of patients with dental disease. From the results of the tests that have been carried out, the match value is obtained for as many as 26 suitable cases. So as to produce a percentage of accuracy of 86.67% in 30 cases. Overall, it can be concluded that the use of the Dempster-Shafer method in this expert system is valid for identifying dental diseases.

Page 2 of 4 | Total Record : 33

 1   2   3   4 

Filter by Year

2022 2024


Reset
Filter By Issues
All Issue Vol. 3 No. 2 (2024): November 2024 Vol 3, No 1 (2024): JUNE 2024 Vol. 3 No. 1 (2024): JUNE 2024 Vol 2, No 1 (2023): VOL 2, NO 1 (2023): VOL 2, NO 1 (2023) Vol 2, No 2 (2023): November Vol. 2 No. 2 (2023): November Vol 1, No 2 (2022): Vol 1, No 2 (2022) Vol 1, No 1 (2022): Vol 1, No 1 (Juni 2022)